© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40321
    Prev
    Next
    INDEX
    Explanations

    content type or taxonomy

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

    The neuron fires on code identifiers for content/post types and their IDs (e.g. “post,” “type,” “ID,” “custom”).

    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
    ↵
    -1.81
    ،
    -1.61
     -
    -1.59
    ."
    -1.42
     the
    -1.42
     "'
    -1.41
     also
    -1.38
    .,
    -1.38
     по
    -1.37
    f
    -1.36
    POSITIVE LOGITS
     服装
    1.47
    دخ
    1.44
    賡
    1.43
    tedy
    1.34
    ﾐ
    1.32
    瀲
    1.30
    $),
    1.29
    ሐ
    1.28
     atento
    1.27
    Czy
    1.23
    Activations Density 0.018%

    No Known Activations