© 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. 100805
    Prev
    Next
    INDEX
    Explanations

    method calls

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

    method calls or member access using the dot operator in programming code.

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

    The neuron fires on numeric literal tokens (integers or floats) 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
    Even
    -1.94
     jugado
    -1.65
    Often
    -1.64
     only
    -1.63
     mochilas
    -1.63
     ήταν
    -1.61
     أيض
    -1.60
     it
    -1.60
    Like
    -1.59
     bestehende
    -1.58
    POSITIVE LOGITS
     It
    2.25
     มัน
    1.98
    niña
    1.75
    ⍢
    1.69
    雰
    1.69
     가장
    1.66
    na
    1.65
    c
    1.64
     anderen
    1.61
     hahaha
    1.59
    Activations Density 0.010%

    No Known Activations