© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1892
    Prev
    Next
    INDEX
    Explanations

    unicode, format, logical, scale

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

    The neuron fires on code‐ or markup‐style delimiter tokens—particularly angle brackets (e.g. “<”, “html”,”>”) and the pipe character (“|”).

    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
     Mus
    -0.80
    MPS
    -0.76
     Conf
    -0.75
    追加
    -0.69
    Mus
    -0.68
    Fak
    -0.67
    Bian
    -0.66
    configs
    -0.65
     conf
    -0.65
     Isabella
    -0.65
    POSITIVE LOGITS
    oks
    0.73
    sile
    0.71
    总经理
    0.67
    procedure
    0.65
     Subcommittee
    0.65
    raya
    0.65
    empty
    0.64
     центр
    0.64
    Registration
    0.62
    gek
    0.62
    Activations Density 0.054%

    No Known Activations