© 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. 39740
    Prev
    Next
    INDEX
    Explanations

    legal, military, or organizational units

    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
     anhänger
    -2.91
    恹
    -2.83
    pecabe
    -2.72
     ſch
    -2.72
    鷥
    -2.67
    𞤢
    -2.64
    衚
    -2.59
    𞤤
    -2.59
     間取り
    -2.58
    ⁧
    -2.56
    POSITIVE LOGITS
    2.80
     For
    2.70
    </h1>
    2.64
     d
    2.58
    </strong>
    2.58
     и
    2.39
    ؟
    2.39
     be
    2.38
    "
    2.36
    」　
    2.33
    Activations Density 0.015%

    No Known Activations