© 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. 65012
    Prev
    Next
    INDEX
    Explanations

    code, programming, and technical terms

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

    The neuron fires on specialized technical identifiers—library/framework/package/class names and other code‐oriented proper nouns.

    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
     作り方
    -1.06
     whiteColor
    -1.06
    急に
    -1.03
     зді
    -1.02
    }%
    -1.02
    ילדים
    -1.00
    Lokal
    -1.00
    橈
    -0.98
    natives
    -0.98
     todella
    -0.97
    POSITIVE LOGITS
     components
    1.06
     or
    1.01
     activities
    0.98
    Num
    0.98
    object
    0.94
    卡
    0.92
    包括
    0.90
     bezahlt
    0.90
    mathbf
    0.89
    Obj
    0.87
    Activations Density 0.116%

    No Known Activations