© 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. 102421
    Prev
    Next
    INDEX
    Explanations

    lively and energetic qualities

    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
    ↵
    -1.82
     Reſ
    -1.69
     such
    -1.63
     creș
    -1.62
    igneurs
    -1.54
     consentimento
    -1.52
    瘣
    -1.52
     esbo
    -1.52
     soyez
    -1.49
     a
    -1.48
    POSITIVE LOGITS
    Despite
    1.66
    This
    1.66
    There
    1.63
    Regardless
    1.62
     –
    1.60
    Contrary
    1.59
    During
    1.59
    These
    1.54
    From
    1.53
     and
    1.50
    Activations Density 0.028%

    No Known Activations