© 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. 11521
    Prev
    Next
    INDEX
    Explanations

    localization keys and code identifiers

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

    the opening quotation mark of a string literal in source code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron fires strongly on the double-quote character, marking the boundaries of string literals.

    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
    '
    -3.59
    7
    -2.80
    3
    -2.80
    9
    -2.77
    6
    -2.73
    4
    -2.39
    想想
    -2.36
    s
    -2.34
    她
    -2.27
    5
    -2.25
    POSITIVE LOGITS
    lgari
    3.09
    derdag
    2.77
    
    2.45
     have
    2.25
    BIÉN
    2.22
    錚
    2.19
    🚙
    2.17
    ,))
    2.16
     you
    2.14
    这般
    2.13
    Activations Density 0.041%

    No Known Activations