© 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. 100358
    Prev
    Next
    INDEX
    Explanations

    candy and candy-related products

    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
     \
    -3.27
    ?"
    -3.19
    (
    -3.02
    en
    -2.80
    art
    -2.78
    in
    -2.69
    -2.64
    an
    -2.63
    on
    -2.53
    f
    -2.36
    POSITIVE LOGITS
    Another
    2.92
    葙
    2.73
    Nearly
    2.56
    When
    2.50
    Surprisingly
    2.48
    Unlike
    2.47
    Their
    2.45
    婞
    2.45
    ومن
    2.42
    ꒥
    2.42
    Activations Density 0.003%

    No Known Activations