© 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. 104430
    Prev
    Next
    INDEX
    Explanations

    parameter lists

    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
     or
    -1.92
     during
    -1.62
     from
    -1.59
     with
    -1.52
     after
    -1.41
     on
    -1.41
     in
    -1.36
     without
    -1.36
     at
    -1.36
     before
    -1.34
    POSITIVE LOGITS
    細かく
    1.16
    摁
    1.15
     vérification
    1.15
    鹇
    1.11
     gruesome
    1.11
     trám
    1.11
    一个个
    1.09
     categorías
    1.08
    upported
    1.06
    voyez
    1.06
    Activations Density 0.064%

    No Known Activations