© 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. 78049
    Prev
    Next
    INDEX
    Explanations

    XML schemas and configurations

    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
     with
    -0.95
     September
    -0.90
     at
    -0.88
    präsident
    -0.86
     alig
    -0.83
    knit
    -0.82
    jez
    -0.80
     going
    -0.79
     all
    -0.76
    waj
    -0.76
    POSITIVE LOGITS
     hombros
    0.98
     boister
    0.96
    américa
    0.95
    اں
    0.87
     drugiej
    0.84
     stipulation
    0.83
     échanges
    0.83
     важно
    0.82
     soooo
    0.82
    ISODE
    0.82
    Activations Density 0.014%

    No Known Activations