© 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. 2287
    Prev
    Next
    INDEX
    Explanations

    integration concepts

    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
     jir
    1.73
    watt
    1.69
     Soldier
    1.69
    eniya
    1.69
    Mailer
    1.62
    メール
    1.62
    霹
    1.58
     NRL
    1.56
     slaw
    1.55
     ENGINE
    1.52
    POSITIVE LOGITS
    Limite
    1.22
    infty
    1.12
     lím
    1.07
    极限
    1.05
     aest
    0.97
    ∞
    0.97
     lim
    0.96
     discont
    0.96
    lastval
    0.95
     extrem
    0.95
    Activations Density 0.042%

    No Known Activations