© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 1457
    Prev
    Next
    INDEX
    Explanations

    Preferences navigation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_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
     unable
    0.80
     their
    0.77
     my
    0.70
     the
    0.70
     Palestine
    0.68
     Czech
    0.67
    ש
    0.66
    ক
    0.65
     February
    0.64
     disillusioned
    0.64
    POSITIVE LOGITS
    🍖
    0.88
    lipid
    0.82
    salmon
    0.81
     entrees
    0.79
    🍭
    0.79
    🛁
    0.79
    EXCEPTION
    0.78
    optimal
    0.78
    ならラクマ
    0.78
    🛋
    0.78
    Activations Density 0.001%

    No Known Activations