© 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. 12-GEMMASCOPE-2-RES-16K
    7. 4448
    Prev
    Next
    INDEX
    Explanations

    positive impact and value

    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_12_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
     とする
    1.40
    ándor
    1.32
     tradisional
    1.26
    őd
    1.23
    entral
    1.22
     melibatkan
    1.21
    expects
    1.21
    弛
    1.19
     morphogenesis
    1.18
    ローバル
    1.18
    POSITIVE LOGITS
     useful
    2.07
    useful
    2.06
     aids
    2.03
     aid
    1.97
     도움이
    1.96
     helpful
    1.95
     utile
    1.95
    帮助
    1.92
     usefulness
    1.88
    有用
    1.88
    Activations Density 0.319%

    No Known Activations