© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83440
    Prev
    Next
    INDEX
    Explanations

    version information or template files

    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
    nord
    -0.73
     évit
    -0.71
    apply
    -0.70
     prouver
    -0.70
    urned
    -0.69
     BRUCE
    -0.69
    beginn
    -0.68
     exclusion
    -0.68
     Imre
    -0.68
     wisata
    -0.67
    POSITIVE LOGITS
     考
    0.65
     EAS
    0.63
     EIF
    0.63
    磺
    0.63
     sentimenti
    0.63
    UNGEN
    0.62
     cutter
    0.62
    ederos
    0.61
    画
    0.61
    澳大利
    0.61
    Activations Density 0.056%

    No Known Activations