© 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. 86832
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron responds to metadata‐style field names or configuration keys (e.g. “affiliates,” “volume,” “content,” “include,” etc.).

    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
    Entry
    -0.71
     champs
    -0.70
    zum
    -0.67
     Tweets
    -0.66
    legal
    -0.66
     قائ
    -0.66
    slip
    -0.65
     AGENCY
    -0.65
     Macintosh
    -0.64
    Zum
    -0.64
    POSITIVE LOGITS
    AED
    0.78
     époux
    0.67
     Ather
    0.65
    gei
    0.65
     issu
    0.64
    ptime
    0.63
     antigos
    0.63
    orienti
    0.62
    loit
    0.62
     oldValue
    0.62
    Activations Density 0.086%

    No Known Activations