© 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. 63412
    Prev
    Next
    INDEX
    Explanations

    code, URLs, and annotations

    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
    Rece
    -0.79
     Abend
    -0.72
     away
    -0.69
     Away
    -0.68
    ommt
    -0.68
    oldt
    -0.65
     ラブ
    -0.63
     Having
    -0.63
    벡
    -0.62
     expressed
    -0.61
    POSITIVE LOGITS
    viel
    0.87
    roffenen
    0.78
    Formulario
    0.77
    phorus
    0.69
    CppMethod
    0.69
    нусы
    0.69
    🚊
    0.69
    orios
    0.69
     分类
    0.66
     vient
    0.65
    Activations Density 0.069%

    No Known Activations