© 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. 22-GEMMASCOPE-RES-131K
    4. 66767
    Prev
    Next
    INDEX
    Explanations

    view details or properties

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

    The neuron activates on occurrences of the word “detail” (in any form, e.g. “detail,” “details,” or “detail page”).

    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
     jesteśmy
    -1.00
     头像
    -0.96
    rainian
    -0.95
    下に
    -0.95
    řízen
    -0.94
    riguez
    -0.94
     EXERCISES
    -0.94
    ombies
    -0.94
    miri
    -0.94
     erfolgreich
    -0.93
    POSITIVE LOGITS
     цветок
    1.11
     hiper
    1.07
    ktive
    1.01
     politika
    1.00
    ͻ
    0.99
     fön
    0.98
    erobic
    0.98
     where
    0.97
    詳
    0.95
     with
    0.94
    Activations Density 0.018%

    No Known Activations