© 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. 10-GEMMASCOPE-RES-131K
    4. 3892
    Prev
    Next
    INDEX
    Explanations

    role, effect, influence

    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_10/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
    扨
    -1.95
    ܊
    -1.93
     arbres
    -1.75
     itinéraire
    -1.74
     aço
    -1.73
    ༥
    -1.71
    梣
    -1.71
     passagers
    -1.70
     apparente
    -1.70
     hébergement
    -1.70
    POSITIVE LOGITS
     of
    3.36
     in
    2.92
     by
    2.30
     or
    2.13
     when
    2.05
     for
    2.02
     which
    2.02
     during
    1.97
     these
    1.87
     that
    1.83
    Activations Density 0.190%

    No Known Activations