© 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. 128791
    Prev
    Next
    INDEX
    Explanations

    court divisions and districts

    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
     «
    -1.63
    This
    -1.57
    T
    -1.48
     »
    -1.45
     …
    -1.42
     ‘‘
    -1.41
    C
    -1.40
    M
    -1.37
     or
    -1.28
     will
    -1.28
    POSITIVE LOGITS
    ⼆
    1.47
     rése
    1.46
     neutre
    1.39
    σουμε
    1.37
    いかない
    1.35
     neuve
    1.35
    鉏
    1.35
    Mvh
    1.34
     effici
    1.33
     délicieux
    1.31
    Activations Density 0.032%

    No Known Activations