© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40361
    Prev
    Next
    INDEX
    Explanations

    interrogative words

    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
     diamant
    -1.84
     bricola
    -1.83
     paradis
    -1.77
     pittores
    -1.76
     rivi
    -1.76
    ÖR
    -1.74
     ananas
    -1.73
     Tahu
    -1.73
     bombe
    -1.73
    豋
    -1.73
    POSITIVE LOGITS
     -
    1.93
    o
    1.75
    </em>
    1.73
     at
    1.67
     on
    1.62
     for
    1.54
     •
    1.46
    ↵↵
    1.45
     even
    1.44
    -
    1.38
    Activations Density 0.039%

    No Known Activations