© 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. 22-GEMMASCOPE-RES-131K
    7. 35655
    Prev
    Next
    INDEX
    Explanations

    creative content or fall transition

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

    The neuron fires on words that appear in section headings or titles (e.g. the first or headline terms of each new segment).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     &
    -0.85
    BeginInit
    -0.79
    تحميل
    -0.77
     gezegd
    -0.75
     púrpura
    -0.74
    ogramm
    -0.73
    챈
    -0.73
     принимать
    -0.71
    Dile
    -0.71
    واع
    -0.70
    POSITIVE LOGITS
     Pued
    0.86
    犀
    0.85
     avanti
    0.84
     Ministre
    0.83
    ÇA
    0.83
    Placement
    0.82
    OLOGIE
    0.82
    🙍
    0.82
     photography
    0.82
     febbraio
    0.81
    Activations Density 0.087%

    No Known Activations