© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10825
    Prev
    Next
    INDEX
    Explanations

    code syntax and identifiers

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

    opening curly braces in programming code.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron responds to numeric 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_10/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
    d
    -2.80
    f
    -2.19
    v
    -2.17
    p
    -2.06
    j
    -2.02
    z
    -1.89
     of
    -1.88
    s
    -1.84
    i
    -1.77
     не
    -1.76
    POSITIVE LOGITS
    皷
    2.28
    癀
    2.11
    selben
    2.11
    ⎔
    2.11
    tráfico
    2.02
     melap
    1.97
     pájaros
    1.95
    
    1.88
     münchen
    1.86
    糴
    1.86
    Activations Density 0.010%

    No Known Activations