© 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. 112473
    Prev
    Next
    INDEX
    Explanations

    law enforcement

    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
    '
    -2.08
     guerrero
    -1.95
     da
    -1.95
     できる
    -1.88
    蕷
    -1.88
    𝖐
    -1.86
    孖
    -1.81
    на
    -1.78
     dei
    -1.77
     de
    -1.74
    POSITIVE LOGITS
    趼
    1.98
    they
    1.94
     is
    1.93
    zelfde
    1.91
    ここは
    1.86
     bona
    1.84
     cũng
    1.84
    ﻊ
    1.81
    狆
    1.81
     extraordinaire
    1.80
    Activations Density 0.002%

    No Known Activations