© 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. 10-GEMMASCOPE-RES-131K
    7. 67924
    Prev
    Next
    INDEX
    Explanations

    initial conditions or states

    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_10/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
    <
    -2.75
    .
    -2.16
    {
    -2.08
    栳
    -2.05
    前来
    -1.81
      
    -1.80
    -
    -1.78
     що
    -1.77
     publiek
    -1.77
    like
    -1.74
    POSITIVE LOGITS
    イヤル
    2.34
    杙
    2.30
    ⎆
    2.28
    varlak
    2.25
    轳
    2.19
    ㌧
    2.17
    メリカ
    2.16
     اولیه
    2.09
    鈊
    2.09
    甚至
    2.02
    Activations Density 0.010%

    No Known Activations