© 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. 34-GEMMASCOPE-RES-131K
    7. 31142
    Prev
    Next
    INDEX
    Explanations

    fee, go, review, license, Park, Tax

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

    The main thing this neuron does is detect standalone numeric tokens (number literals) 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_34/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
     کھ
    -0.89
     geluk
    -0.89
    に出て
    -0.85
    vied
    -0.84
    παν
    -0.84
    DAQ
    -0.80
     πολ
    -0.79
    Ƃ
    -0.78
     sué
    -0.78
    fused
    -0.77
    POSITIVE LOGITS
     floral
    1.01
    orderBy
    0.89
     tree
    0.88
     persönliche
    0.84
     Tree
    0.84
     würd
    0.81
    樹
    0.80
    嶇
    0.78
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.77
    ೂ
    0.76
    Activations Density 0.000%

    No Known Activations