© 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. 15564
    Prev
    Next
    INDEX
    Explanations

    code definitions and assignments

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

    The neuron strongly activates on numeric tokens—i.e. literal numbers (and numbers embedded in identifiers or file‐path/version strings) 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_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
     kompeti
    -1.42
    Fär
    -1.35
     régiment
    -1.34
    értel
    -1.34
     signifikan
    -1.33
     великолеп
    -1.31
    Awal
    -1.31
    Gör
    -1.30
    rechten
    -1.30
     siè
    -1.30
    POSITIVE LOGITS
    ?
    1.39
    M
    1.29
    ta
    1.27
     this
    1.26
    L
    1.25
    E
    1.25
    !
    1.25
    ^
    1.25
    S
    1.25
    T
    1.25
    Activations Density 0.057%

    No Known Activations