© 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. 75737
    Prev
    Next
    INDEX
    Explanations

    EXO members and K-pop

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

    The neuron selectively activates on document‐level metadata tokens—things like bracketed names or labels, numeric codes, section markers, and similar annotation rather than ordinary text.

    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
     окончания
    -0.72
     ます
    -0.71
     verurs
    -0.69
     柴
    -0.69
     DAT
    -0.68
     جلوگیری
    -0.67
    DATUM
    -0.67
    moo
    -0.66
    chemist
    -0.66
     resourceCulture
    -0.66
    POSITIVE LOGITS
     EXO
    1.38
    EXO
    1.22
     Exo
    1.12
     exo
    1.07
    Exo
    1.01
    exo
    0.93
     Baek
    0.93
     Kris
    0.91
    Kris
    0.88
     Kai
    0.83
    Activations Density 0.014%

    No Known Activations