© 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. 10-GEMMASCOPE-RES-131K
    7. 103742
    Prev
    Next
    INDEX
    Explanations

    XML and code structure

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

    indentation or whitespace at the beginning of lines in code.

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

    The neuron fires on numeric literals (like integers and floating‐point constants) in 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_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
     it
    -2.02
     and
    -1.96
     in
    -1.71
     there
    -1.68
     at
    -1.65
     "
    -1.58
     '
    -1.57
     its
    -1.45
     (
    -1.28
     to
    -1.24
    POSITIVE LOGITS
     frança
    1.83
     conster
    1.75
     fuper
    1.70
     vernac
    1.69
     incess
    1.69
     fevere
    1.68
     blanda
    1.68
     meriva
    1.65
     prenn
    1.64
     torino
    1.64
    Activations Density 0.026%

    No Known Activations