© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78818
    Prev
    Next
    INDEX
    Explanations

    words starting with 'od'

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

    The neuron fires on occurrences of the letter sequence “odo” (as found in genus or species names like Odostomia, Babesia odocoilei, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     понадоби
    -0.83
    auces
    -0.83
     hablaba
    -0.79
     моменты
    -0.76
     Didier
    -0.75
    tamanya
    -0.75
    ίζ
    -0.75
    垭
    -0.73
    ollett
    -0.73
    CUSTOM
    -0.73
    POSITIVE LOGITS
    红色
    0.85
    苓
    0.76
    jukan
    0.75
    вный
    0.74
     pronounced
    0.71
     Eurovision
    0.70
    واد
    0.69
    建筑
    0.68
     oda
    0.68
    щин
    0.68
    Activations Density 0.028%

    No Known Activations