© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 13590
    Prev
    Next
    INDEX
    Explanations

    punctuation and numbers

    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
    ="
    0.81
     grün
    0.79
     $=
    0.77
     $=$
    0.77
     DEPENDENCIA
    0.76
     auriculares
    0.74
     squadra
    0.73
     singleArray
    0.73
    ౪
    0.73
     ="
    0.73
    POSITIVE LOGITS
    SPOT
    0.78
    ప్పుడు
    0.70
    腸
    0.70
    romantic
    0.68
    navigate
    0.68
    other
    0.68
    issi
    0.68
    the
    0.67
    條件
    0.67
    DR
    0.67
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.