© 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. 22-GEMMASCOPE-RES-131K
    4. 11258
    Prev
    Next
    INDEX
    Explanations

    language connectors and specific nouns

    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
     to
    -2.09
     and
    -2.02
     by
    -1.45
     with
    -1.34
     from
    -1.29
     for
    -1.28
     without
    -1.25
     until
    -1.21
     if
    -1.20
     then
    -1.20
    POSITIVE LOGITS
     bacté
    1.49
     nombreuses
    1.30
     seules
    1.20
     Sénat
    1.20
     indescri
    1.19
    怱
    1.19
    continuing
    1.18
    Especially
    1.18
    significantly
    1.16
     folyam
    1.16
    Activations Density 0.109%

    No Known Activations