© 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. 40538
    Prev
    Next
    INDEX
    Explanations

    detecting code imports

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

    The neuron activates on numeric literals (integers or decimals) in the text.

    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
     навіть
    -1.53
     in
    -1.51
    __":
    -1.49
    sierung
    -1.41
    ется
    -1.38
    glichen
    -1.31
     even
    -1.30
    }),
    -1.23
    вів
    -1.22
    馳走
    -1.21
    POSITIVE LOGITS
     this
    1.59
     you
    1.30
     ebenfalls
    1.28
    牐
    1.19
     suom
    1.19
     muñeco
    1.18
    fois
    1.18
     everything
    1.17
     membunuh
    1.14
     viewDidLoad
    1.13
    Activations Density 0.021%

    No Known Activations