© 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. 6725
    Prev
    Next
    INDEX
    Explanations

    go to the tab

    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
    直送
    1.83
    戕
    1.61
    utzerklärung
    1.60
    otard
    1.56
    sj
    1.55
    壽
    1.54
     declara
    1.53
    遨
    1.53
     kapan
    1.52
    ご紹介
    1.52
    POSITIVE LOGITS
     Crescent
    1.53
     spurs
    1.45
     titers
    1.43
     sublattice
    1.42
    ocused
    1.41
    تبه
    1.25
    convex
    1.25
     neige
    1.25
    ⠄
    1.24
    евич
    1.24
    Activations Density 0.019%

    No Known Activations