© 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. 10-GEMMASCOPE-RES-131K
    7. 70883
    Prev
    Next
    INDEX
    Explanations

    not so [adjective/adverb]

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ఽ
    -2.50
    .
    -2.23
     nettoyer
    -2.16
     ralenti
    -2.13
     Perſ
    -2.02
     exceptionally
    -2.02
     všem
    -1.95
    罴
    -1.95
    僰
    -1.95
     ถ้า
    -1.95
    POSITIVE LOGITS
    。”
    1.89
    Also
    1.79
    Even
    1.74
    Although
    1.69
     achieves
    1.67
    This
    1.65
    Despite
    1.63
    !!!!!
    1.63
    There
    1.59
    的
    1.59
    Activations Density 0.009%

    No Known Activations