© 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
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 218948
    Prev
    Next
    INDEX
    Explanations

    from C or our menus

    np_acts-logits-general · gemini-2.5-flash-lite

    Art, Style, dehydration, introduced

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ండు
    0.54
    де
    0.52
    ਦ
    0.50
    iž
    0.49
    챕
    0.49
    참
    0.46
    че
    0.46
    顾问
    0.46
    ంద
    0.46
     дела
    0.45
    POSITIVE LOGITS
    rystals
    0.52
     Density
    0.47
     densities
    0.46
     Eight
    0.42
     density
    0.42
     abilities
    0.41
     Barton
    0.41
     milliliters
    0.41
     processors
    0.40
     Cin
    0.40
    Activations Density 0.002%

    No Known Activations