© 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. 129355
    Prev
    Next
    INDEX
    Explanations

    The neuron activates on numeric literals (tokens containing digits) in code or config files.

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

    code structure declaration

    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
     inginkan
    -1.08
    蜊
    -0.98
     AspNetCore
    -0.98
    ⚕
    -0.97
     requestCode
    -0.97
    لیسی
    -0.97
    ∓
    -0.96
    — 
    -0.96
    xvii
    -0.96
    ≳
    -0.95
    POSITIVE LOGITS
     was
    1.05
     may
    0.98
    ard
    0.89
     öffentlichen
    0.88
    ins
    0.88
    ed
    0.88
     formal
    0.87
     europäischen
    0.86
     späteren
    0.85
    ck
    0.85
    Activations Density 0.001%

    No Known Activations