© 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. 22-GEMMASCOPE-RES-131K
    7. 129178
    Prev
    Next
    INDEX
    Explanations

    quantity and degree

    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_22/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
    必要がある
    -1.96
    の準備
    -1.94
    為に
    -1.73
    ようです
    -1.72
    際に
    -1.68
    必要があります
    -1.63
    きち
    -1.55
    を行い
    -1.52
    に戻る
    -1.50
    #%%
    -1.50
    POSITIVE LOGITS
     in
    2.59
     on
    2.52
     from
    2.08
     for
    1.96
    は
    1.92
    などが
    1.85
    を
    1.81
     with
    1.79
     about
    1.72
     by
    1.70
    Activations Density 0.035%

    No Known Activations