© 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. 37591
    Prev
    Next
    INDEX
    Explanations

    introducing specific examples

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

    such information

    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
     всі
    0.77
     которому
    0.75
     который
    0.73
    াত্মক
    0.73
     Į
    0.72
     and
    0.71
    ন
    0.71
     kojem
    0.70
    𝟯
    0.69
    ര്‍
    0.69
    POSITIVE LOGITS
    s
    1.05
    t
    1.02
    (
    0.95
    c
    0.89
    such
    0.87
    p
    0.84
     an
    0.83
    be
    0.80
    اً
    0.80
    おお
    0.79
    Activations Density 0.065%

    No Known Activations