© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 1604
    Prev
    Next
    INDEX
    Explanations

    property acquisitions

    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
    ట్స్‌
    0.70
    ట్స్
    0.67
    myer
    0.64
     τ
    0.63
    )<
    0.63
    PrintWriter
    0.63
     minded
    0.62
    snp
    0.62
    ალური
    0.62
     rooting
    0.62
    POSITIVE LOGITS
     longue
    0.95
     persones
    0.91
     Jésus
    0.89
     modalités
    0.89
    І
    0.85
     personnes
    0.84
     catégories
    0.84
    다
    0.84
     kilomètres
    0.82
     centaines
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.