© 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. 75872
    Prev
    Next
    INDEX
    Explanations

    License

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

    The neuron fires on file‐or module‐level header tokens—things like “proto,” “hibernate,” XML/DOCTYPES, license markers, #includes, etc.—i.e. it flags the lines that name or declare the file’s format or top‐level metadata.

    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
     many
    -0.87
     dirigir
    -0.77
    ypsies
    -0.75
    ⑴
    -0.72
     occupation
    -0.72
     with
    -0.72
    ılan
    -0.71
    gapa
    -0.71
     हुई
    -0.71
    ESIS
    -0.70
    POSITIVE LOGITS
    rometers
    0.91
     фотография
    0.88
    throws
    0.84
    考虑到
    0.81
    fato
    0.79
     안
    0.77
    ὸς
    0.76
    lioni
    0.75
    没有任何
    0.74
     IW
    0.73
    Activations Density 0.002%

    No Known Activations