© 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. 143677
    Prev
    Next
    INDEX
    Explanations

    synthetic, bats, general, atmosphere

    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
    и
    0.43
    ÿ
    0.42
    ме
    0.41
    Matches
    0.40
    ɒ
    0.40
     Statistical
    0.40
     Canonical
    0.39
    чи
    0.39
    Ajax
    0.38
    ằ
    0.38
    POSITIVE LOGITS
     continuar
    0.45
     brunâtre
    0.43
     suede
    0.43
     vicino
    0.42
     Nutz
    0.42
     continuer
    0.42
     montrent
    0.41
     снять
    0.41
    袢
    0.41
     Spitz
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.