© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 109312
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    The neuron is highly sensitive to tokens that are part of source‐code license or comment metadata (e.g. comment delimiters like “*/”, license keywords, file‐extension markers such as “.svg”, “blog” in a URL path).

    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
     contratar
    -0.71
    PostExecute
    -0.71
    の内
    -0.67
     CF
    -0.66
    yu
    -0.65
    IRR
    -0.65
     Region
    -0.64
     inse
    -0.64
     Block
    -0.63
     Mila
    -0.63
    POSITIVE LOGITS
    (`${
    0.85
     shedding
    0.69
    listings
    0.69
    |_{\
    0.68
    pools
    0.67
    ')(
    0.67
     доби
    0.66
    ⌠
    0.66
    ificant
    0.65
     sebut
    0.65
    Activations Density 0.067%

    No Known Activations