© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14259
    Prev
    Next
    INDEX
    Explanations

    Slavic and Portuguese affirmative words

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

    This neuron activates on sentence-initial discourse markers or connector words (e.g. adverbs/conjunctions like “Ну,” “Ще,” “Generalmente,” “Может,” “Ainda,” 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
     its
    -1.95
     yine
    -1.64
    $
    -1.63
    5
    -1.56
     devido
    -1.55
     ใน
    -1.55
    The
    -1.55
     antes
    -1.46
    :
    -1.39
    ۷
    -1.39
    POSITIVE LOGITS
    鱟
    1.54
    禇
    1.34
    縂
    1.30
    獁
    1.29
     restaurante
    1.29
    を見ながら
    1.28
    Ambos
    1.27
     帅
    1.27
     pelaku
    1.24
    Gruppo
    1.24
    Activations Density 0.014%

    No Known Activations