© 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. 10-GEMMASCOPE-RES-131K
    4. 42823
    Prev
    Next
    INDEX
    Explanations

    JSON configuration

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

    This neuron detects long runs of leading whitespace (indentation) in structured (e.g. JSON-like) text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     in
    -1.76
    2
    -1.52
     of
    -1.46
    );
    -1.41
     at
    -1.38
    8
    -1.38
    ,”
    -1.38
     from
    -1.37
    3
    -1.34
    6
    -1.34
    POSITIVE LOGITS
     you
    1.65
     acoged
    1.60
    嵛
    1.56
     próprias
    1.55
     conoció
    1.55
    Slightly
    1.49
    Mainly
    1.48
    ⟣
    1.46
    挫折
    1.46
     divertidas
    1.45
    Activations Density 0.040%

    No Known Activations