© 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. 33003
    Prev
    Next
    INDEX
    Explanations

    copyright and licensing details

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

    The neuron fires on runs of leading whitespace (indentation) and related block‐delimiting tokens (like “do” and “@”) that mark code structure.

    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
     into
    -0.72
     мес
    -0.70
     Owing
    -0.64
    你先
    -0.63
    case
    -0.63
     слід
    -0.63
    itech
    -0.62
     собі
    -0.61
     Nw
    -0.61
    andia
    -0.61
    POSITIVE LOGITS
     Cunha
    0.78
    pax
    0.75
    Karn
    0.73
     Karn
    0.73
     Gemma
    0.69
    žius
    0.69
     Chasse
    0.68
     Fiske
    0.68
    sworth
    0.67
    Accommodation
    0.67
    Activations Density 0.082%

    No Known Activations