© 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. 102867
    Prev
    Next
    INDEX
    Explanations

    common word pairings

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

    This neuron fires on document‐structure markers and metadata delimiters—e.g. YAML front-matter separators (“---”) and license/copyright headers.

    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
     progressBar
    -0.85
     свои
    -0.84
     zor
    -0.81
     tenis
    -0.79
    телей
    -0.78
     boto
    -0.78
     ț
    -0.78
     toit
    -0.77
    oudoune
    -0.77
     skru
    -0.75
    POSITIVE LOGITS
    chufe
    0.79
     compresión
    0.79
    overset
    0.78
     alcune
    0.77
     powy
    0.76
     Generated
    0.76
    ிக்
    0.76
    alım
    0.75
    Huile
    0.75
    θρώ
    0.75
    Activations Density 0.000%

    No Known Activations