© 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. 63816
    Prev
    Next
    INDEX
    Explanations

    license version 2

    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
    Autoritní
    -0.86
     suor
    -0.82
    tempel
    -0.79
     Dining
    -0.76
     étr
    -0.75
     Birth
    -0.74
    ⓘ
    -0.74
    érience
    -0.73
     gick
    -0.73
    UDP
    -0.73
    POSITIVE LOGITS
     commence
    0.88
     RESPOND
    0.83
     occidentalis
    0.82
    是否有
    0.78
    ፤
    0.77
     immor
    0.76
    スポンサーリンク
    0.76
     hilfiger
    0.75
     renew
    0.75
    ская
    0.75
    Activations Density 0.002%

    No Known Activations