© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 39058
    Prev
    Next
    INDEX
    Explanations

    topics and reasons

    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
    -1.80
     from
    -1.74
     for
    -1.74
     at
    -1.65
     on
    -1.55
     can
    -1.30
     as
    -1.30
     in
    -1.29
     using
    -1.27
     without
    -1.23
    POSITIVE LOGITS
     conster
    1.41
     semel
    1.29
    recently
    1.27
    depuis
    1.27
    Afficher
    1.24
    veyard
    1.20
    mainly
    1.19
    zation
    1.18
    supposed
    1.17
     smör
    1.17
    Activations Density 0.020%

    No Known Activations