© 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. 10-GEMMASCOPE-RES-131K
    7. 68221
    Prev
    Next
    INDEX
    Explanations

    copyright notices

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

    The neuron activates on comma punctuation 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
     longtime
    -2.05
    what
    -1.98
     What
    -1.83
     How
    -1.75
    emporio
    -1.69
    改为
    -1.66
     завжди
    -1.64
     cansado
    -1.63
    ufes
    -1.60
    <bos>
    -1.59
    POSITIVE LOGITS
    —
    1.78
    ↵↵
    1.71
     eigenen
    1.67
    ي
    1.66
    ется
    1.58
    佷
    1.58
    ់
    1.55
    ہ
    1.53
    ramientas
    1.52
    ز
    1.44
    Activations Density 0.059%

    No Known Activations