© 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. 1751
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    ug
    0.85
    س
    0.83
    🏸
    0.80
    ົງ
    0.80
     COSTS
    0.78
     площадь
    0.77
    सरकार
    0.77
    высо
    0.76
    uskan
    0.75
    oresis
    0.74
    POSITIVE LOGITS
    theless
    0.86
    IN
    0.80
    pdf
    0.78
     volutpat
    0.78
    ี
    0.78
     poter
    0.77
     reales
    0.76
     récentes
    0.76
     différentes
    0.75
    ertation
    0.74
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.