© 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. 33276
    Prev
    Next
    INDEX
    Explanations

    sequence completion

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

    This neuron detects technical phrasing related to spread-spectrum or code-division multiple-access communication systems.

    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
    Технические
    -0.70
    anthes
    -0.69
     lesen
    -0.69
    酸
    -0.69
    皇子
    -0.68
     Klasse
    -0.68
     babys
    -0.67
     contatto
    -0.67
     Mila
    -0.66
    acidade
    -0.66
    POSITIVE LOGITS
     sequence
    1.02
     spreading
    0.98
     Spreading
    0.97
    Bark
    0.91
    sequence
    0.91
     chipping
    0.90
    dwell
    0.85
     Dwell
    0.84
    spreading
    0.84
     spread
    0.83
    Activations Density 0.076%

    No Known Activations