© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 12-GEMMASCOPE-2-RES-16K
    7. 6028
    Prev
    Next
    INDEX
    Explanations

    code structures

    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
    忍者
    1.04
    resar
    0.98
    erapeut
    0.97
     *\
    0.96
    eldorf
    0.95
    }^{*}=\
    0.94
    karma
    0.94
    ASIA
    0.94
    ashvili
    0.93
    */}
    0.93
    POSITIVE LOGITS
    oun
    1.63
     Wiss
    1.58
    播放
    1.48
     marqu
    1.44
     Johnstone
    1.40
     Ново
    1.40
     Gough
    1.37
     Chois
    1.35
     quizz
    1.34
     Фо
    1.32
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.