© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 12561
    Prev
    Next
    INDEX
    Explanations

    digital

    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_7_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
    Архівовано
    2.88
    DrawerToggle
    2.86
    ᑭ
    2.74
     скры
    2.73
    ాలను
    2.70
    BOOL
    2.61
    ↞
    2.52
    tfrac
    2.51
    JButton
    2.48
     TextAppearance
    2.45
    POSITIVE LOGITS
    an
    2.92
    elem
    2.83
    تس
    2.69
    고
    2.69
    dru
    2.61
    ا
    2.61
    구
    2.57
    াং
    2.52
    sé
    2.49
    anish
    2.48
    Activations Density 0.022%

    No Known Activations