© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87006
    Prev
    Next
    INDEX
    Explanations

    preliminary drawings or sketches

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

    The neuron is keyed to heading‐style tokens (titles, subtitles, and other section‐header words) in structured or encyclopedic text.

    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
    plaque
    -0.90
    āci
    -0.88
    publishing
    -0.88
    ัฐ
    -0.84
    ỏi
    -0.84
    Irlande
    -0.84
     картины
    -0.82
    anom
    -0.81
     làn
    -0.81
    outheast
    -0.81
    POSITIVE LOGITS
     sketch
    3.39
     sketches
    3.39
     sketched
    2.52
    sketch
    2.52
     sketching
    2.50
     Sketch
    2.27
     preliminary
    2.19
    Sketch
    2.17
     Sketches
    2.11
     rough
    2.03
    Activations Density 0.041%

    No Known Activations