© 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. 68074
    Prev
    Next
    INDEX
    Explanations

    coconut, palm, olive, elephants

    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
    0
    -1.55
     ”
    -1.50
    www
    -1.38
     and
    -1.38
    連れて
    -1.36
    (\
    -1.33
    ꯴
    -1.31
    在她
    -1.26
    ところは
    -1.26
    面白い
    -1.25
    POSITIVE LOGITS
    儈
    1.52
    頽
    1.46
    夢想
    1.44
    逦
    1.44
    ICIOS
    1.44
    وحة
    1.43
     deine
    1.38
     corsa
    1.34
    ྃ
    1.34
     orar
    1.33
    Activations Density 0.017%

    No Known Activations