© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 47512
    Prev
    Next
    INDEX
    Explanations

    assignment or definition keywords

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

    The neuron activates on code-like parameter or configuration keys (e.g. function arguments, option names, or settings identifiers).

    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
     our
    -2.03
     you
    -1.97
     it
    -1.63
     there
    -1.55
     your
    -1.52
     characterized
    -1.52
    (\
    -1.43
     my
    -1.40
     where
    -1.37
     huellas
    -1.27
    POSITIVE LOGITS
    zzá
    1.39
     جديدة
    1.38
    angering
    1.37
    APPY
    1.37
    
    1.35
    ącz
    1.34
     새로운
    1.30
     extraordin
    1.28
    年初
    1.28
    ств
    1.27
    Activations Density 0.061%

    No Known Activations