© 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. 112518
    Prev
    Next
    INDEX
    Explanations

    court citations with numbers and years

    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
     Japão
    -1.81
     juiz
    -1.80
    龔
    -1.73
    ⇴
    -1.73
    ​.
    -1.67
     veículo
    -1.66
     afirmó
    -1.63
     pertenec
    -1.62
    ･･･
    -1.60
    .•
    -1.60
    POSITIVE LOGITS
    r
    2.33
    C
    2.19
     is
    2.16
    ’
    2.14
    l
    2.08
    W
    1.98
    ?”
    1.98
    D
    1.97
    }
    1.93
    J
    1.91
    Activations Density 0.000%

    No Known Activations