© 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. 72694
    Prev
    Next
    INDEX
    Explanations

    c/c++ include statements

    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
     RECOMM
    -1.14
    ısından
    -1.05
     CONTRIBUT
    -1.00
    不但
    -0.95
    ternut
    -0.93
    ronomie
    -0.89
    Вопрос
    -0.88
     Almighty
    -0.86
    thodox
    -0.85
    ђу
    -0.85
    POSITIVE LOGITS
     also
    1.26
     también
    1.08
     نیز
    1.06
     også
    1.02
    別の
    1.00
     here
    0.98
    ＄
    0.96
     également
    0.93
    BATTERY
    0.93
     också
    0.93
    Activations Density 0.020%

    No Known Activations