© 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. 2539
    Prev
    Next
    INDEX
    Explanations

    useful for a specific purpose

    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
    以下的
    2.02
    做得
    1.99
    有所
    1.94
     SAME
    1.90
     Blossom
    1.89
     aforesaid
    1.85
    下来的
    1.85
    ()==
    1.85
    binghamton
    1.85
     shenanigans
    1.84
    POSITIVE LOGITS
     önemlidir
    1.17
     šte
    1.05
     majeur
    1.05
    ="#"
    1.03
    unctive
    1.03
     רבים
    1.00
     complemento
    0.99
     complementing
    0.98
    juvant
    0.95
    ダー
    0.95
    Activations Density 0.287%

    No Known Activations