© 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. 246175
    Prev
    Next
    INDEX
    Explanations

    a pet, two, mentor, year, elementary

    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
    ር
    0.50
    noticed
    0.48
    የ
    0.46
    रे
    0.44
    וני
    0.43
    ն
    0.43
    য়
    0.43
    น
    0.42
    וק
    0.42
     Mechanics
    0.42
    POSITIVE LOGITS
     ERISA
    0.50
    人了
    0.50
    圻
    0.49
     pover
    0.48
     pollute
    0.48
    眯
    0.48
     ouvr
    0.48
     Toxicol
    0.47
     rischi
    0.47
     necesit
    0.47
    Activations Density 0.000%

    No Known Activations