© 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. 129434
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric literals (sequences of digits) in code or configuration text.

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

    environment variables and configuration

    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
     this
    -1.71
    VolleyError
    -1.20
     any
    -1.16
    ३
    -1.16
    simov
    -1.14
     lutego
    -1.14
    ="">
    -1.13
    --;
    -1.09
     (!__
    -1.09
    ६
    -1.09
    POSITIVE LOGITS
    蜮
    1.15
     accompagner
    1.12
     familières
    1.09
     séjours
    1.07
     dépenses
    1.06
     siè
    1.05
     étend
    1.05
     твоя
    1.05
     loca
    1.04
     péné
    1.04
    Activations Density 0.009%

    No Known Activations