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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3243
    Prev
    Next
    INDEX
    Explanations

    coding and web responses

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    vello
    -0.82
    Dacă
    -0.80
    Ngoài
    -0.78
    OSPH
    -0.77
     ピンク
    -0.76
    以下
    -0.76
    さえ
    -0.74
    젼
    -0.73
     максима
    -0.73
    нон
    -0.73
    POSITIVE LOGITS
     status
    0.86
    ůže
    0.82
     efforts
    0.82
    続いて
    0.81
    htë
    0.80
     Safe
    0.77
     prompted
    0.77
    ('.',
    0.76
    昵称
    0.76
     Möglich
    0.75
    Activations Density 0.003%

    No Known Activations