© 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. 117775
    Prev
    Next
    INDEX
    Explanations

    document startups and technical introductions

    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
    оп
    -0.81
    brengen
    -0.77
    =#{
    -0.77
    bhp
    -0.76
    uuuuu
    -0.75
    tote
    -0.75
    InkWell
    -0.75
    🧘
    -0.74
    gün
    -0.74
    Caring
    -0.74
    POSITIVE LOGITS
     DSA
    0.90
    捌
    0.84
    テム
    0.82
    ows
    0.82
    ポーチ
    0.82
     sitios
    0.81
     essi
    0.80
     controle
    0.80
     lloc
    0.80
    ws
    0.79
    Activations Density 0.000%

    No Known Activations