© 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. 34-GEMMASCOPE-RES-131K
    7. 116127
    Prev
    Next
    INDEX
    Explanations

    r followed by specific characters

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

    The neuron fires almost exclusively on the standalone token “r” (as used in code—e.g. a one‐letter variable or regex identifier).

    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
    flies
    -0.94
     primeras
    -0.89
     喜欢
    -0.88
     宝宝
    -0.85
    itest
    -0.83
     anything
    -0.83
    x
    -0.81
     worries
    -0.80
     choices
    -0.79
    flt
    -0.79
    POSITIVE LOGITS
     r
    1.38
    сков
    0.77
    够
    0.77
    専門店
    0.77
    Ꮕ
    0.74
     ん
    0.73
    ixen
    0.72
    رر
    0.72
    ране
    0.72
    seek
    0.72
    Activations Density 0.021%

    No Known Activations