© 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. 54220
    Prev
    Next
    INDEX
    Explanations

    parsing strings and separators

    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
     Secondo
    0.48
    څ
    0.46
    Ả
    0.44
     materiale
    0.43
     മൈ
    0.43
    さが
    0.42
     اُن
    0.42
     odyssey
    0.42
    直径
    0.42
     katth
    0.42
    POSITIVE LOGITS
    adjust
    0.48
    )$}
    0.45
    itting
    0.44
    फिर
    0.44
    eraient
    0.43
     जल्द
    0.42
     thermostat
    0.42
    i
    0.42
     항상
    0.41
    เสมอ
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.