© 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. 22-GEMMASCOPE-RES-131K
    7. 68516
    Prev
    Next
    INDEX
    Explanations

    citations and addresses

    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_22/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
     from
    -1.16
     kuris
    -0.91
     on
    -0.90
    hidup
    -0.83
    டன்
    -0.82
    Ƿ
    -0.82
     extraordinarily
    -0.79
     specifik
    -0.77
    TAR
    -0.77
     specifically
    -0.76
    POSITIVE LOGITS
     utilisé
    0.93
     represen
    0.88
     seren
    0.88
     facil
    0.86
     لله
    0.85
    WhiteSpace
    0.84
     promulg
    0.83
     Enables
    0.83
     presenti
    0.82
     완
    0.82
    Activations Density 0.004%

    No Known Activations