© 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. 78841
    Prev
    Next
    INDEX
    Explanations

    professional medical advice

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

    properties or attributes in software configuration or programming code.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    This neuron detects configuration or annotation keywords that disable or exclude elements (e.g. “ignoreUnknown,” “JsonIgnoreProperties,” “exclude‐result‐prefixes”).

    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
    scalatest
    -0.84
    losseum
    -0.83
    gungen
    -0.79
    сё
    -0.76
    おります
    -0.75
    krb
    -0.74
    kými
    -0.73
    thington
    -0.73
     iria
    -0.73
    لع
    -0.72
    POSITIVE LOGITS
     répé
    0.98
    óri
    0.88
    臨床
    0.85
    šej
    0.81
     altogether
    0.81
    чна
    0.79
    ilor
    0.76
    intrag
    0.75
    干扰
    0.75
    tirar
    0.75
    Activations Density 0.064%

    No Known Activations