© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 43501
    Prev
    Next
    INDEX
    Explanations

    multiplication and division

    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
    ,;
    -2.13
     spectacular
    -2.08
     astounding
    -2.06
    ౮
    -2.02
     renowned
    -2.02
     astonishing
    -2.00
     revered
    -2.00
     acclaimed
    -2.00
    蛲
    -1.98
     momentous
    -1.97
    POSITIVE LOGITS
     by
    2.78
    :
    2.56
     from
    2.33
     or
    2.30
     through
    2.11
     with
    2.06
     there
    2.05
     that
    1.99
     using
    1.93
     on
    1.88
    Activations Density 0.010%

    No Known Activations