© 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. 35624
    Prev
    Next
    INDEX
    Explanations

    I hope

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

    the presence of standalone numerical tokens (digits or Roman-numeral style tokens) in the text.

    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
     Facile
    -0.97
     عاشقانه
    -0.92
     Musée
    -0.92
     baie
    -0.91
     klima
    -0.91
     Lumière
    -0.90
     kitab
    -0.90
    🌌
    -0.90
     pouvons
    -0.89
    Aplikasi
    -0.89
    POSITIVE LOGITS
     czter
    1.07
     two
    0.97
     aimed
    0.96
     trzech
    0.94
    colos
    0.93
     move
    0.92
     yesterday
    0.90
    ラウンド
    0.90
     recomendado
    0.88
     coger
    0.88
    Activations Density 0.008%

    No Known Activations