© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 130095
    Prev
    Next
    INDEX
    Explanations

    code elements and parameters

    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
     and
    -1.97
     here
    -1.38
    っているので
    -1.29
     of
    -1.23
    chern
    -1.20
    狡
    -1.20
     who
    -1.19
     This
    -1.19
    zval
    -1.16
    denly
    -1.15
    POSITIVE LOGITS
    を
    1.27
    )、
    1.16
    写真は
    1.16
    技術
    1.13
    );
    1.13
    か
    1.10
    }
    1.05
     raisons
    1.04
    Parfait
    1.03
     LIABLE
    1.03
    Activations Density 0.001%

    No Known Activations