© 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. 129013
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on section‐header and metadata labels (e.g. document titles, stats/info headings, markup tags) rather than running text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    specifications and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     nossa
    -1.10
    beelding
    -0.98
    droje
    -0.93
     என்ப
    -0.92
    atecas
    -0.90
    共和
    -0.90
    tamiento
    -0.89
    ESSIONAL
    -0.89
     Hivatalos
    -0.89
     hjemmes
    -0.88
    POSITIVE LOGITS
     including
    1.24
     height
    1.20
    including
    1.14
    包括
    1.06
     size
    1.05
     parameters
    1.05
     width
    0.98
    INCLUDING
    0.97
     length
    0.96
     name
    0.96
    Activations Density 0.149%

    No Known Activations