© 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. 4166
    Prev
    Next
    INDEX
    Explanations

    any additional setup

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

    The neuron responds to programming‐style boilerplate tokens—especially preprocessor directives (e.g. “#include” and header names) and uppercase license/disclaimer keywords.

    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
     sync
    -0.73
     Rocco
    -0.71
     Wren
    -0.70
     bytes
    -0.69
     keep
    -0.67
    imedes
    -0.67
     filho
    -0.65
    Ở
    -0.65
     lemons
    -0.65
    minist
    -0.65
    POSITIVE LOGITS
     khô
    0.71
    ሑ
    0.71
     다음
    0.69
     없습니다
    0.67
     UMA
    0.67
    bedrijf
    0.66
    recovered
    0.66
     HNO
    0.66
    duğu
    0.66
    switchTo
    0.65
    Activations Density 0.070%

    No Known Activations