© 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. 45244
    Prev
    Next
    INDEX
    Explanations

    creating and setting values

    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
     his
    -1.58
     our
    -1.53
     the
    -1.41
    他的
    -1.37
    萣
    -1.35
     alltid
    -1.35
    änden
    -1.34
    または
    -1.33
    および
    -1.27
     clôture
    -1.27
    POSITIVE LOGITS
     would
    1.73
    0
    1.61
     because
    1.33
     puedas
    1.31
     could
    1.31
    '
    1.27
    </h2>
    1.26
    1.24
    acterísticas
    1.24
     '
    1.24
    Activations Density 0.049%
    No Known Activations