© 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. 10-GEMMASCOPE-RES-131K
    4. 19682
    Prev
    Next
    INDEX
    Explanations

    seasons and causes

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

    This neuron activates on standalone, heading‐style tokens (often title‐case or section‐label words) that appear at the start of lines or document sections.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ↵
    -1.54
     not
    -1.37
     whose
    -1.23
     That
    -1.19
     which
    -1.18
     ikke
    -1.17
     însă
    -1.13
    melden
    -1.12
    しない
    -1.11
    ற்ப
    -1.11
    POSITIVE LOGITS
    ﹌
    1.40
     berücksich
    1.37
    Também
    1.30
    ashvili
    1.27
    @[+][
    1.27
    QWidget
    1.25
     verbessern
    1.23
     @"/
    1.23
    ForType
    1.23
     maroon
    1.23
    Activations Density 0.104%

    No Known Activations