© 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. 14036
    Prev
    Next
    INDEX
    Explanations

    parsing characters or single letters

    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
    ເລັກ
    0.43
    过度
    0.43
    籁
    0.42
    വസ്ഥ
    0.42
    рма
    0.41
    かの
    0.41
    ാനുള്ള
    0.41
     অধর
    0.41
    的情況
    0.40
    다
    0.40
    POSITIVE LOGITS
     crea
    0.47
    ylle
    0.45
     prove
    0.44
     síntomas
    0.44
     proje
    0.43
     biomarkers
    0.42
     entrants
    0.42
     壁
    0.42
     carácter
    0.41
    polyline
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.