© 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. 1955
    Prev
    Next
    INDEX
    Explanations

    landing and impacts

    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
    बिग
    1.33
    생
    1.33
     involution
    1.32
     shrinkage
    1.31
     atrophy
    1.30
    叙
    1.30
    Months
    1.27
     문제입니다
    1.20
    环境变量
    1.19
     یخچال
    1.19
    POSITIVE LOGITS
    hits
    1.59
     hitting
    1.58
     acert
    1.58
    hitting
    1.58
    狠狠
    1.52
    HIT
    1.50
    🎯
    1.50
    ชน
    1.49
     hitbox
    1.47
     hits
    1.47
    Activations Density 0.427%

    No Known Activations