© 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. 14694
    Prev
    Next
    INDEX
    Explanations

    FileNotFound Exception, crooked teeth

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

    This neuron activates on CamelCase or other code‐style identifiers and technical class names.

    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
    -3.69
    from
    -3.16
    t
    -2.92
    ть
    -2.66
    慙
    -2.63
    with
    -2.59
    </i>
    -2.56
    饜
    -2.55
    柃
    -2.53
    軚
    -2.50
    POSITIVE LOGITS
    姈
    3.06
    鼇
    2.78
    ⬈
    2.72
    .
    2.64
    𐐪
    2.63
    ᡵ
    2.39
     Eighty
    2.28
    ᥬ
    2.28
     antemano
    2.27
     Somewhat
    2.25
    Activations Density 0.002%

    No Known Activations