© 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. 138430
    Prev
    Next
    INDEX
    Explanations

    foreign words, numbers, punctuation

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

    deep body sensations

    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
     plumage
    0.47
    igheter
    0.46
     environments
    0.44
     in
    0.43
     handbags
    0.43
    obb
    0.42
     baggage
    0.42
    在
    0.42
     configuration
    0.42
    igraphy
    0.42
    POSITIVE LOGITS
     días
    0.57
     necesito
    0.56
     giorni
    0.53
     Física
    0.52
     Ñ
    0.50
     día
    0.49
     desea
    0.49
     pierws
    0.49
     ciento
    0.48
     miedo
    0.48
    Activations Density 0.000%

    No Known Activations