© 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. 15292
    Prev
    Next
    INDEX
    Explanations

    conditional logic and questions

    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
    ’
    -2.11
     the
    -2.06
     and
    -1.83
     \
    -1.77
     What
    -1.70
     From
    -1.67
     it
    -1.63
     That
    -1.58
    .,
    -1.56
    with
    -1.52
    POSITIVE LOGITS
    </h5>
    1.90
    ところは
    1.76
     vardı
    1.76
     REACTOR
    1.66
     sofá
    1.66
     iglesia
    1.59
    PTEMBER
    1.59
    ⃠
    1.58
     nación
    1.56
     cuna
    1.55
    Activations Density 0.002%

    No Known Activations