© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 67896
    Prev
    Next
    INDEX
    Explanations

    identifier followed by specific keyword or punctuation

    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_10/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
     in
    -1.38
     with
    -1.28
     even
    -1.20
     démocratie
    -1.20
     this
    -1.20
     like
    -1.17
     despite
    -1.17
     on
    -1.15
     punten
    -1.13
    othermic
    -1.12
    POSITIVE LOGITS
     finalmente
    1.26
     laquelle
    1.25
     eventualmente
    1.23
    现在的
    1.23
     sekarang
    1.16
     судеб
    1.16
     Projektu
    1.15
     ktorá
    1.13
    不仅
    1.12
    有时候
    1.11
    Activations Density 0.101%

    No Known Activations