© 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. 242
    Prev
    Next
    INDEX
    Explanations

    programming code snippets

    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
     with
    -1.30
     after
    -1.19
     for
    -1.10
     at
    -1.03
     from
    -1.02
     if
    -0.99
     because
    -0.97
    codehaus
    -0.96
     perpetually
    -0.96
     within
    -0.95
    POSITIVE LOGITS
     новой
    1.16
     écrire
    1.16
    눙
    1.16
     effets
    1.15
     FRANK
    1.13
     générer
    1.12
     ELIZABETH
    1.12
    olingo
    1.12
     ΤΟ
    1.11
    エピ
    1.10
    Activations Density 0.034%

    No Known Activations