© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 25544
    Prev
    Next
    INDEX
    Explanations

    help text

    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
    囤
    -0.75
    worthy
    -0.74
    mData
    -0.72
    rook
    -0.71
    跳舞
    -0.69
     skull
    -0.66
    AntiForgery
    -0.66
     danken
    -0.65
    pooled
    -0.65
     suitors
    -0.65
    POSITIVE LOGITS
    asil
    0.72
     movimento
    0.67
     PFS
    0.66
     averaging
    0.63
     rethink
    0.63
     households
    0.63
     変
    0.63
    interpre
    0.62
    tende
    0.62
    inset
    0.62
    Activations Density 0.086%

    No Known Activations