© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 65212
    Prev
    Next
    INDEX
    Explanations

    Indic language or script

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

    This neuron detects Devanagari (Hindi/Marathi) script characters.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    which
    -3.52
    er
    -3.09
    F
    -2.89
    to
    -2.88
    in
    -2.70
    D
    -2.69
    A
    -2.69
    C
    -2.52
    n
    -2.50
    ?
    -2.44
    POSITIVE LOGITS
     was
    2.39
     awful
    2.34
    嬲
    2.33
     to
    2.33
    
    2.25
    biamo
    2.23
    雳
    2.23
     místa
    2.17
    NOWLEDG
    2.16
    这意味着
    2.16
    Activations Density 0.000%

    No Known Activations