© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2127
    Prev
    Next
    INDEX
    Explanations

    multiplication operations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Excited
    1.21
    靳
    1.19
     DETAIL
    1.19
     FID
    1.18
    andidate
    1.17
    romad
    1.16
    avkhat
    1.16
    FID
    1.14
    冨
    1.13
    endid
    1.13
    POSITIVE LOGITS
    times
    1.52
    Times
    1.50
     Times
    1.24
    TIMES
    1.18
     times
    1.14
     TIMES
    1.12
    ×
    1.07
    タブ
    1.05
     ×
    1.02
    ニー
    0.94
    Activations Density 0.090%

    No Known Activations