© 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. 87012
    Prev
    Next
    INDEX
    Explanations

    japanese syllables ka and ki

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

    The neuron specializes in detecting Hindi case-marking particles (e.g. ka, ki, no).

    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
    hiva
    -1.97
    genden
    -1.81
    ErrUnexpectedEOF
    -1.79
    ătate
    -1.77
    strator
    -1.74
    sburg
    -1.74
    tonsoft
    -1.68
    ogues
    -1.68
    
    -1.67
    ressee
    -1.66
    POSITIVE LOGITS
    </h2>
    2.16
    —
    2.09
    "
    2.08
     —
    2.06
    </em>
    1.89
     insistence
    1.66
     établir
    1.64
    larger
    1.63
    slightly
    1.60
     experiences
    1.59
    Activations Density 0.008%

    No Known Activations