© 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. 22-GEMMASCOPE-RES-131K
    7. 33485
    Prev
    Next
    INDEX
    Explanations

    request body

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

    The neuron fires on occurrences of the token “body” (as in HTTP/API request or response bodies).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     seleccionadas
    -1.95
     —
    -1.87
    </h3>
    -1.86
     usadas
    -1.67
    umumkan
    -1.66
     verschillende
    -1.66
    UCION
    -1.62
     conforto
    -1.62
    which
    -1.61
    acterísticas
    -1.60
    POSITIVE LOGITS
    If
    2.16
    𐐪
    2.03
    These
    1.80
    で
    1.79
    izoen
    1.77
     olabilir
    1.73
    ᠊
    1.71
    .");
    1.66
    With
    1.65
    quelize
    1.64
    Activations Density 0.005%

    No Known Activations