© 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. 26378
    Prev
    Next
    INDEX
    Explanations

    code delimiters

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

    The neuron strongly activates on standalone numeric literals (numbers) 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
    aly
    -0.85
    也算是
    -0.84
     traversing
    -0.83
     pół
    -0.82
    reado
    -0.80
     einander
    -0.79
     réalis
    -0.78
    ĕ
    -0.77
     about
    -0.77
    估计
    -0.77
    POSITIVE LOGITS
    анта
    0.81
     squid
    0.81
     Llu
    0.79
    lawan
    0.78
    ándo
    0.77
    டும்
    0.76
    ถ้า
    0.75
    ló
    0.75
    推奨
    0.74
     daca
    0.73
    Activations Density 0.010%

    No Known Activations