© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1089
    Prev
    Next
    INDEX
    Explanations

    total and all

    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
     vyš
    1.16
    &-
    1.13
     rapidez
    1.09
     niedr
    1.08
     demasiado
    1.07
     szint
    1.06
    踌
    1.05
    慎
    1.04
     niž
    1.04
    sizing
    1.03
    POSITIVE LOGITS
     total
    2.63
     tota
    2.41
    total
    2.28
     TOTAL
    2.15
     keseluruhan
    2.14
     totale
    2.02
     전체
    1.98
    Total
    1.97
    جمالي
    1.92
    TOTAL
    1.91
    Activations Density 0.952%

    No Known Activations