© 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. 117916
    Prev
    Next
    INDEX
    Explanations

    report, transmit, or control information

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

    This neuron strongly activates on highly technical wireless‐communications specification language—particularly descriptions of reference signals, measurement reports, and protocol procedures.

    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
    bez
    -0.79
     роли
    -0.76
    hatenablog
    -0.75
    cherichia
    -0.71
     जाते
    -0.70
    ird
    -0.70
    плы
    -0.69
     العين
    -0.69
     Curie
    -0.69
    ค้า
    -0.69
    POSITIVE LOGITS
    PUS
    0.94
    slots
    0.90
    Feedback
    0.88
     procesu
    0.79
     feedback
    0.78
    ulers
    0.78
     opportunity
    0.77
     ocasión
    0.76
    UCI
    0.76
     Verpflichtung
    0.76
    Activations Density 0.047%

    No Known Activations