© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 66610
    Prev
    Next
    INDEX
    Explanations

    words after names/symbols

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

    This neuron detects underscore characters used in programming identifiers (i.e., the “_” in variable, constant, or type names).

    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
    lossians
    -1.63
    +"\
    -1.43
     некоторых
    -1.34
    1
    -1.32
    сматри
    -1.32
     {}\
    -1.31
     *
    -1.30
     "\\
    -1.30
    .$_
    -1.29
    屺
    -1.29
    POSITIVE LOGITS
     from
    1.84
     of
    1.72
     at
    1.71
     where
    1.59
     it
    1.59
     which
    1.44
     unterschied
    1.42
     value
    1.41
     chiusura
    1.41
    PARE
    1.38
    Activations Density 0.001%

    No Known Activations