© 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. 15700
    Prev
    Next
    INDEX
    Explanations

    sql query execution

    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
    :
    -1.05
     and
    -0.91
    家
    -0.91
    tick
    -0.89
     tracks
    -0.87
    amm
    -0.86
     az
    -0.86
     ss
    -0.85
     య
    -0.85
     ay
    -0.85
    POSITIVE LOGITS
    お疲れ様でした
    1.02
    ífico
    1.01
    ＊＊＊
    1.00
    OBJETIVOS
    0.98
     likened
    0.96
    安倍
    0.94
    忏
    0.93
    的对象
    0.92
    ごめんなさい
    0.91
    本日の
    0.90
    Activations Density 0.014%

    No Known Activations