© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64874
    Prev
    Next
    INDEX
    Explanations

    The ASF license

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

    The neuron activates strongly on sequences of whitespace used to indent and format comment‐block lines (e.g. the leading spaces and asterisks in Apache‐style license headers).

    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
     just
    -0.86
     tertawa
    -0.86
    mappedBy
    -0.84
     perdana
    -0.84
     that
    -0.84
     Being
    -0.83
     keter
    -0.82
    /*"
    -0.81
     norske
    -0.79
     fà
    -0.79
    POSITIVE LOGITS
     essas
    0.90
    同时也
    0.89
    Instead
    0.85
     famed
    0.85
     pensamientos
    0.85
    ::~
    0.83
    kově
    0.82
     certamente
    0.82
     버튼
    0.79
    brtc
    0.79
    Activations Density 0.002%

    No Known Activations