© 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. 128631
    Prev
    Next
    INDEX
    Explanations

    express or implied

    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
     velho
    -1.70
     "..\..\..\
    -1.66
     \
    -1.66
     ikke
    -1.63
    缡
    -1.61
    </h1>
    -1.59
    蛱
    -1.57
    apimachinery
    -1.55
     livro
    -1.52
    </h4>
    -1.52
    POSITIVE LOGITS
     and
    2.08
     or
    1.89
    　　-
    1.60
    -
    1.57
    ſtanding
    1.54
    There
    1.53
     selection
    1.52
    To
    1.46
    Despite
    1.45
    殞
    1.42
    Activations Density 0.020%

    No Known Activations