© 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. 70339
    Prev
    Next
    INDEX
    Explanations

    names, numbers, ordinals

    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
     adesivo
    -1.76
     concorda
    -1.72
     isolamento
    -1.70
    Цита
    -1.70
     eivät
    -1.58
     FISHING
    -1.56
     INSTALLATION
    -1.55
     europé
    -1.55
     SEÑ
    -1.55
     pharmacie
    -1.54
    POSITIVE LOGITS
     as
    2.22
     from
    2.00
     is
    1.73
     with
    1.65
     to
    1.54
     and
    1.50
     or
    1.49
     That
    1.42
    uzz
    1.39
            
    1.38
    Activations Density 0.001%

    No Known Activations