© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 73587
    Prev
    Next
    INDEX
    Explanations

    then, or follow-up actions

    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
     según
    -0.94
     tropicales
    -0.92
     jsou
    -0.92
     our
    -0.91
     especially
    -0.88
     rezultat
    -0.88
     részt
    -0.87
    imageio
    -0.87
    できない
    -0.86
     luôn
    -0.86
    POSITIVE LOGITS
     then
    1.48
    ここから
    1.14
    このまま
    1.09
     prosegu
    1.06
     continuare
    1.04
    Продол
    1.02
    證明
    0.96
     proceeded
    0.93
     proceed
    0.93
    さぁ
    0.88
    Activations Density 0.056%

    No Known Activations