© 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. 8295
    Prev
    Next
    INDEX
    Explanations

    .htm files

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

    The neuron strongly fires on occurrences of the “htm” token (i.e. references to .htm filenames or links).

    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
    ࿚
    -2.77
    鲽
    -2.72
    瑧
    -2.69
     که
    -2.64
    鸰
    -2.56
    阋
    -2.52
    akterysty
    -2.52
    龊
    -2.50
    闿
    -2.47
    谞
    -2.45
    POSITIVE LOGITS
    [
    2.94
    </strong>
    2.53
    (
    2.47
    ...
    2.45
    ?"
    2.44
    2.42
    {
    2.42
    筇
    2.41
              
    2.39
    ou
    2.23
    Activations Density 0.001%

    No Known Activations