© 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. 6339
    Prev
    Next
    INDEX
    Explanations

    over at places or time periods

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

    over

    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
     or
    0.90
    ோ
    0.86
    orpio
    0.83
    及ひ
    0.79
    ل
    0.75
    میم
    0.74
     нулю
    0.74
     تعالیٰ
    0.73
     июле
    0.72
     ноябре
    0.72
    POSITIVE LOGITS
    (
    1.35
    -
    1.15
    A
    0.91
    D
    0.86
    '
    0.86
    E
    0.85
    "
    0.83
    S
    0.81
    www
    0.81
     over
    0.80
    Activations Density 0.101%

    No Known Activations