© 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. 34-GEMMASCOPE-RES-131K
    7. 107043
    Prev
    Next
    INDEX
    Explanations

    X out of Y

    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_34/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
    คุณ
    -0.80
    之前
    -0.77
    日
    -0.76
    玉米
    -0.74
    ilim
    -0.73
    onChanged
    -0.70
    ходы
    -0.69
     Seil
    -0.69
    best
    -0.68
    入
    -0.68
    POSITIVE LOGITS
    getMax
    0.81
     '.';
    0.80
    borderBottom
    0.78
    ogeneity
    0.75
     neque
    0.75
    彼らは
    0.75
    繇
    0.74
    '],'
    0.74
    naeus
    0.73
    —¡
    0.73
    Activations Density 0.045%

    No Known Activations