© 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. 65657
    Prev
    Next
    INDEX
    Explanations

    names and dates

    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
    ᅥ
    -0.87
     whet
    -0.80
     variaciones
    -0.76
    greSQL
    -0.75
     then
    -0.74
     hermoso
    -0.74
    kve
    -0.73
     Bạn
    -0.73
     empêcher
    -0.73
     here
    -0.71
    POSITIVE LOGITS
    mill
    0.93
     Miller
    0.91
    Gilbert
    0.90
    rights
    0.89
     stile
    0.85
     silt
    0.84
     rist
    0.82
    viez
    0.82
    Miller
    0.81
    Silva
    0.81
    Activations Density 0.011%

    No Known Activations