© 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. 756
    Prev
    Next
    INDEX
    Explanations

    code and technical documentation

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

    The neuron fires on import statements and module/class names from the Telegram API (e.g. “telegram.ext,” protocol entities, handlers, etc.).

    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
    xion
    -0.76
     concentrate
    -0.70
    urte
    -0.69
     ALLOW
    -0.68
    atii
    -0.68
    ESSMENT
    -0.68
    뻐
    -0.67
    uyu
    -0.67
    église
    -0.66
     紹介
    -0.65
    POSITIVE LOGITS
    aut
    0.84
    audio
    0.79
    uyla
    0.71
    Edited
    0.71
    Updates
    0.71
     Bot
    0.68
    交渉
    0.68
     Passport
    0.68
     Document
    0.68
    Answer
    0.68
    Activations Density 0.009%

    No Known Activations