© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84200
    Prev
    Next
    INDEX
    Explanations

    My Heavenly

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

    The neuron is strongly activated by Lisp-style opening parentheses (i.e. “(”).

    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
    薗
    -0.81
     Allein
    -0.78
     洛
    -0.76
     recruiter
    -0.74
    极致
    -0.71
     detailing
    -0.71
    iedy
    -0.69
    繇
    -0.69
     Galo
    -0.69
     Imm
    -0.69
    POSITIVE LOGITS
    let
    0.91
    PROG
    0.84
     let
    0.84
     when
    0.81
    ->
    0.79
     membres
    0.79
     със
    0.78
     MEMBER
    0.77
    LET
    0.76
    cond
    0.76
    Activations Density 0.041%

    No Known Activations