© 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. 80986
    Prev
    Next
    INDEX
    Explanations

    file extensions or technical formats

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

    This neuron strongly activates on code comment markers and boilerplate licensing or copyright text (e.g. “//”, “reserved”, large license‐block punctuation).

    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
     verlä
    -0.79
     Vy
    -0.76
    acti
    -0.75
    Enciclopedia
    -0.75
     활
    -0.71
    δί
    -0.71
    cored
    -0.71
    entered
    -0.70
    ウイルス
    -0.69
    baidu
    -0.69
    POSITIVE LOGITS
     vorbei
    0.99
     orienti
    0.98
    lehnt
    0.84
     beteiligt
    0.82
    ới
    0.79
     termites
    0.79
     bete
    0.76
     teilnehmen
    0.73
     gemessen
    0.71
     denken
    0.70
    Activations Density 0.017%

    No Known Activations