© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 31806
    Prev
    Next
    INDEX
    Explanations

    code initialization or declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .
    2.05
    is
    1.90
    (
    1.86
    m
    1.77
    ال
    1.70
    l
    1.69
    {
    1.67
    in
    1.64
    f
    1.64
    t
    1.62
    POSITIVE LOGITS
     doesn
    1.48
     insolvent
    1.39
     unwavering
    1.34
     deseo
    1.30
     modesty
    1.30
     azienda
    1.30
    聩
    1.29
     volonté
    1.27
     Comissão
    1.27
     início
    1.27
    Activations Density 0.037%

    No Known Activations