© 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. 22-GEMMASCOPE-RES-131K
    7. 35195
    Prev
    Next
    INDEX
    Explanations

    code snippets

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

    This neuron detects code‐snippet tokens—programming keywords, identifiers, punctuation, and symbols typical of source code.

    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
     интерьера
    -1.14
    vyš
    -1.05
    lepší
    -0.98
    JSONException
    -0.98
     стоимо
    -0.96
     yalnızca
    -0.96
     dört
    -0.96
     интерьер
    -0.96
     páns
    -0.96
     what
    -0.94
    POSITIVE LOGITS
    这个时候
    1.16
    这时候
    1.13
    хоз
    1.07
     devez
    1.03
     anormal
    1.02
     Nå
    1.02
     Detta
    1.00
    젊
    1.00
     bestens
    0.98
    鏝
    0.98
    Activations Density 0.042%

    No Known Activations