© 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. 129553
    Prev
    Next
    INDEX
    Explanations

    job or performance

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

    The neuron fires on occurrences of the string “gig” (in any case or as part of longer words like “Gigabit,” “gig-economy,” etc.).

    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
    ☫
    -3.25
    ⢫
    -3.19
    婠
    -2.97
    闥
    -2.86
    ⢧
    -2.84
    ཋ
    -2.78
    豨
    -2.72
    殽
    -2.69
    艄
    -2.69
    縂
    -2.69
    POSITIVE LOGITS
     was
    2.84
    ,
    2.67
    u
    2.66
    ’
    2.55
    //
    2.53
    蜮
    2.53
    All
    2.50
    已经
    2.47
    ">
    2.44
     n
    2.41
    Activations Density 0.002%

    No Known Activations