© 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. 181986
    Prev
    Next
    INDEX
    Explanations

    setup, range, ends, current, 2

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

    Beyond phrases like Neg

    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
    鍝
    0.46
    蚋
    0.46
     Receivable
    0.44
    贲
    0.44
     CLOSED
    0.43
    טור
    0.43
    િર
    0.43
     Thereafter
    0.42
    ឫ
    0.42
    ส
    0.41
    POSITIVE LOGITS
    hayati
    0.55
    leg
    0.54
    print
    0.53
    wet
    0.48
     biodegrad
    0.47
     legumes
    0.46
     hazy
    0.46
     transluc
    0.45
    lege
    0.43
     moins
    0.43
    Activations Density 0.002%

    No Known Activations