© 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. 129400
    Prev
    Next
    INDEX
    Explanations

    constant values and conditions

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

    The neuron activates on instances of the word “constant,” i.e. mentions of parameters or quantities being held constant.

    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
     ocasi
    -1.53
    跸
    -1.50
     rękaw
    -1.50
    菝
    -1.49
    鸶
    -1.46
     exemplifies
    -1.46
     Anſ
    -1.45
    蹰
    -1.42
     hvid
    -1.42
    Cuando
    -1.42
    POSITIVE LOGITS
     one
    2.11
     or
    1.97
     for
    1.88
     during
    1.86
     in
    1.70
     until
    1.67
     despite
    1.66
     throughout
    1.65
     there
    1.63
     using
    1.62
    Activations Density 0.061%

    No Known Activations