© 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. 1004
    Prev
    Next
    INDEX
    Explanations

    language, errors, licensing, Lebanon

    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
    ि
    0.76
    الن
    0.63
    多い
    0.63
    ঠিক
    0.62
    য়োজন
    0.62
     diminish
    0.61
     vapors
    0.60
     subscripts
    0.60
    الى
    0.59
     unconditional
    0.59
    POSITIVE LOGITS
    ra
    0.96
    rif
    0.92
    ☢
    0.83
     quelquefois
    0.79
    /\/
    0.78
    rö
    0.76
     насеко
    0.75
    FBSDK
    0.75
    ल
    0.73
     tragedia
    0.73
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.