© 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. 102381
    Prev
    Next
    INDEX
    Explanations

    at Surfacesat Marsat Sundayat schizophreniaat Statesat room

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

    The neuron selectively activates on words and tokens that occur in document headings, titles, section labels, or other emphasized “headline” text (e.g. major technical terms or proper‐noun phrases set off as titles).

    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
     not
    -1.38
     that
    -1.34
     into
    -1.29
    を使
    -1.22
    を使う
    -1.18
     dalamnya
    -1.17
    个
    -1.16
     seguire
    -1.13
     auffi
    -1.09
    irc
    -1.06
    POSITIVE LOGITS
    interopRequire
    1.36
     where
    1.32
    
    1.20
    𝖒
    1.18
    アップデート
    1.14
    ViewImports
    1.13
     級
    1.12
    šiu
    1.11
    Controllo
    1.11
    ском
    1.11
    Activations Density 0.403%

    No Known Activations