© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 3159
    Prev
    Next
    INDEX
    Explanations

    multiplication calculations

    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_12_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    brechen
    2.07
    oden
    2.05
     sorpresa
    2.00
    vare
    1.90
     grandi
    1.88
    думы
    1.85
    創意
    1.84
    hatian
    1.82
    مرات
    1.81
    譎
    1.80
    POSITIVE LOGITS
     massaging
    1.09
     echocardi
    1.05
     getN
    0.97
    Edd
    0.91
     tabulated
    0.89
     Pele
    0.89
     sphing
    0.88
     blackjack
    0.88
    𝓮
    0.85
     Neymar
    0.84
    Activations Density 0.005%

    No Known Activations