© 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. 55909
    Prev
    Next
    INDEX
    Explanations

    operators and code

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

    This neuron fires on tokens that appear in software‐license header blocks—e.g. license keywords (Licensed, you), punctuation ("/", ".", quotes, parentheses), and import‐path slashes.

    oai_token-act-pair · o4-miniTriggered 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
    èlement
    -0.72
    地上
    -0.70
    RATE
    -0.70
     ciascuno
    -0.68
    antle
    -0.66
    BATCH
    -0.66
    同上
    -0.66
     willow
    -0.66
     хозя
    -0.65
     zap
    -0.65
    POSITIVE LOGITS
    neuf
    0.81
    две
    0.73
    ディガン
    0.69
    ologiques
    0.69
     Underwear
    0.68
    cava
    0.68
    newtheorem
    0.68
     நி
    0.67
    Портал
    0.67
    ndal
    0.67
    Activations Density 0.036%

    No Known Activations