© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47937
    Prev
    Next
    INDEX
    Explanations

    lower bounds, Studywise minimization

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on geographic and administrative place names (regions, countries, districts) and their punctuated context in location‐description sentences.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    periods that end sentences, particularly in formal or legal documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    mentions of geopolitical/administrative entities with accompanying structured facts like dates, numbers, or identifiers.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⡼
    -0.83
     Schreiber
    -0.79
     Phantas
    -0.76
    ectious
    -0.75
    Ventajas
    -0.75
    DOES
    -0.75
     karton
    -0.74
    Followed
    -0.73
     diversified
    -0.73
     kred
    -0.71
    POSITIVE LOGITS
    マップ
    0.85
     igjen
    0.82
     朝
    0.82
    nessione
    0.79
    observation
    0.76
    源码
    0.75
    ℙ
    0.74
    šas
    0.72
     быть
    0.72
    寛
    0.71
    Activations Density 0.001%

    No Known Activations