© 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. 42152
    Prev
    Next
    INDEX
    Explanations

    information, descriptive labels, sections

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

    The neuron fires on isolated headings or section‐title labels (e.g. standalone words like “Information,” “Overview,” “Profile,” “Feature,” etc.).

    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
     ؛
    -1.40
    </u>
    -1.30
     cruda
    -1.27
    、
    -1.20
     cristiana
    -1.20
     connue
    -1.18
     velha
    -1.16
     maestra
    -1.16
     метров
    -1.15
     груди
    -1.15
    POSITIVE LOGITS
     and
    2.48
     jego
    1.48
     instead
    1.33
     based
    1.30
    livejournal
    1.30
     цього
    1.23
     while
    1.20
    ไลน์
    1.19
     actually
    1.18
     ネタバレ
    1.18
    Activations Density 0.186%

    No Known Activations