© 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. 15601
    Prev
    Next
    INDEX
    Explanations

    k-means initialization

    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
    ี
    0.93
    よう
    0.86
    ifah
    0.85
    ましょう
    0.81
    یت
    0.78
    段时间
    0.78
    ことが
    0.77
    یدن
    0.76
     dusk
    0.75
    рай
    0.75
    POSITIVE LOGITS
    나
    0.77
     import
    0.77
    ন
    0.75
    Archive
    0.71
    Ahora
    0.71
     সংবিধান
    0.71
    scrape
    0.71
    Roasted
    0.71
    Interior
    0.70
    Estamos
    0.70
    Activations Density 0.000%

    No Known Activations