© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49121
    Prev
    Next
    INDEX
    Explanations

    under, below, sous

    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
     truk
    -0.77
     schnelle
    -0.72
     Einbau
    -0.71
     作り方
    -0.71
    ्यालय
    -0.70
    трим
    -0.69
    initData
    -0.69
    Créditos
    -0.69
     bok
    -0.68
     университе
    -0.68
    POSITIVE LOGITS
    viation
    0.80
    inander
    0.79
    Ǧ
    0.77
     слой
    0.77
    Dive
    0.76
    lih
    0.76
    bný
    0.76
    gatron
    0.75
     soumis
    0.75
    namespace
    0.74
    Activations Density 0.012%

    No Known Activations