© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128890
    Prev
    Next
    INDEX
    Explanations

    The neuron is triggered by numeric literal tokens in code (i.e. it detects numbers).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    python class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     Août
    -1.33
     Chambres
    -1.27
    hlten
    -1.26
     exemplaires
    -1.24
     appétit
    -1.21
     Présentation
    -1.20
     britannique
    -1.18
    ㎏
    -1.18
     TabLayout
    -1.18
     Commentaires
    -1.16
    POSITIVE LOGITS
     if
    1.42
    ↵↵
    1.28
     and
    1.23
     praktischen
    1.22
    これが
    1.17
     Betracht
    1.16
     will
    1.13
    娅
    1.09
     wesentlichen
    1.09
     offiziellen
    1.07
    Activations Density 0.020%

    No Known Activations