© 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. 63634
    Prev
    Next
    INDEX
    Explanations

    URLs and specific punctuation

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

    The neuron is keyed to detect numeric tokens and URL‐ or download‐style fragments (digits, “http”, “.com”, “Download”, 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
     momentarily
    -0.82
    axaca
    -0.75
    sivité
    -0.74
     انگلیسی
    -0.73
    closeButton
    -0.72
    руется
    -0.71
     ironically
    -0.71
     relatively
    -0.70
    čiau
    -0.70
     месе
    -0.70
    POSITIVE LOGITS
     '&#
    0.97
     három
    0.95
     introduit
    0.94
    に見える
    0.93
     растения
    0.92
     ,'
    0.92
    urate
    0.88
    containing
    0.86
    turned
    0.86
     rencontr
    0.86
    Activations Density 0.003%

    No Known Activations