© 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. 2288
    Prev
    Next
    INDEX
    Explanations

    code snippets and technical writing

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

    The neuron is keyed to whitespace‐formatting tokens (e.g. space/newline markers and CSS “white-space: pre” declarations).

    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
     quadrant
    -0.78
    pati
    -0.72
     Fathers
    -0.72
    Deep
    -0.69
    anganese
    -0.68
     quartet
    -0.68
    deep
    -0.67
     wesentlichen
    -0.67
    ISS
    -0.67
     Deep
    -0.66
    POSITIVE LOGITS
    胆
    0.70
     ティー
    0.69
     Guru
    0.65
     ciutat
    0.65
     Grenze
    0.64
    ༘
    0.64
     дис
    0.62
     Source
    0.62
     stav
    0.60
    臨時
    0.60
    Activations Density 0.050%

    No Known Activations