© 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. 2151
    Prev
    Next
    INDEX
    Explanations

    lists of types and groups

    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
    总是
    1.72
    總是
    1.68
     okam
    1.65
    就不会
    1.63
     시간이
    1.63
    énés
    1.61
     suele
    1.59
    蹭
    1.57
    ведения
    1.55
     завжди
    1.55
    POSITIVE LOGITS
     apiece
    2.07
     total
    2.01
     TOTAL
    1.90
    各有
    1.90
     totaling
    1.86
     grouped
    1.84
    合計
    1.82
     totalling
    1.79
    total
    1.78
     suddiv
    1.77
    Activations Density 0.494%

    No Known Activations