© 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. 18836
    Prev
    Next
    INDEX
    Explanations

    interior spaces and numerators

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

    numerator of fractions

    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
    。
    0.44
    IFT
    0.43
    als
    0.42
    iots
    0.41
    ;</
    0.40
    IF
    0.40
    ۔
    0.39
    ALS
    0.38
    ITLE
    0.38
    0.38
    POSITIVE LOGITS
     ανάπτυ
    0.46
     کشتی
    0.43
    哐
    0.43
    厲
    0.42
    㥉
    0.42
    紧张
    0.42
     tableView
    0.40
     фай
    0.40
     <=>
    0.40
    পালের
    0.40
    Activations Density 0.000%

    No Known Activations