© 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. 22-GEMMASCOPE-RES-131K
    7. 15478
    Prev
    Next
    INDEX
    Explanations

    multiplication and division operations

    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_22/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
     the
    -3.14
     become
    -2.17
     When
    -2.09
    </td>
    -1.88
    During
    -1.80
    With
    -1.80
     There
    -1.79
     Anfang
    -1.73
    One
    -1.70
     From
    -1.70
    POSITIVE LOGITS
    🫃
    2.33
    骉
    2.23
    歺
    2.16
    毟
    2.03
    ⬈
    2.02
    が含ま
    2.02
     yaka
    1.98
    ⽌
    1.95
     mily
    1.95
    嗩
    1.95
    Activations Density 0.005%

    No Known Activations