© 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. 13941
    Prev
    Next
    INDEX
    Explanations

    carcass, casing

    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
    饪
    -2.77
    .
    -2.50
    ."
    -2.27
    鳐
    -2.23
     "
    -2.22
    梣
    -2.20
    摃
    -2.14
     foray
    -2.08
    </i>
    -2.06
     تعدى
    -2.06
    POSITIVE LOGITS
    ’
    3.41
    i
    2.83
    ⵌ
    2.59
    '
    2.55
     “
    2.48
    錼
    2.27
     изделий
    2.05
    x
    2.03
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    1.99
    ’，
    1.97
    Activations Density 0.017%

    No Known Activations