© 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. 22-GEMMASCOPE-RES-131K
    7. 128120
    Prev
    Next
    INDEX
    Explanations

    technical and scientific 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
     also
    -1.56
     الشرطة
    -1.13
     inoltre
    -1.09
    one
    -1.08
    of
    -1.06
    چنین
    -1.04
     correto
    -1.04
    agliari
    -1.04
     của
    -1.04
     également
    -1.04
    POSITIVE LOGITS
    utilisateur
    1.13
    bürger
    1.12
    styrelsen
    1.11
     ۱۳۸
    1.10
    Instrumented
    1.10
    んじゃ
    1.10
    áciu
    1.09
    Basta
    1.09
    hkan
    1.07
     insbesondere
    1.07
    Activations Density 0.068%

    No Known Activations