© 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
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1859
    Prev
    Next
    INDEX
    Explanations

    likely to suspect

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
    ↵↵
    1.74
    s
    1.47
    tub
    1.25
    のを
    1.05
    melt
    1.03
     bondage
    0.98
     proportionately
    0.95
     gul
    0.91
     eup
    0.91
     twitch
    0.91
    POSITIVE LOGITS
    ئيس
    1.77
    Bechyné
    1.68
    đi
    1.68
    ೇಖ
    1.56
    ığımız
    1.56
    chyné
    1.56
    <blockquote>
    1.50
     gravedad
    1.49
    onnées
    1.49
     !}{
    1.49
    Activations Density 0.037%

    No Known Activations