© 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. 78699
    Prev
    Next
    INDEX
    Explanations

    math formulas or code

    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
    してみました
    -0.81
     волосы
    -0.75
    bosity
    -0.74
    說道
    -0.73
    __((
    -0.70
    羟
    -0.69
    いただいた
    -0.69
    asmussen
    -0.69
     VILL
    -0.69
     leit
    -0.68
    POSITIVE LOGITS
    マーク
    1.03
    danger
    0.85
     danger
    0.82
     hereto
    0.82
    osd
    0.79
     mammo
    0.79
     TEX
    0.78
    normal
    0.77
    //*/
    0.75
     tex
    0.74
    Activations Density 0.003%

    No Known Activations