© 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. 1143
    Prev
    Next
    INDEX
    Explanations

    listing components or states

    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
     rêver
    -1.40
    鵙
    -1.36
    ᕮ
    -1.35
     vientos
    -1.31
    ANDS
    -1.29
    怱
    -1.27
     jego
    -1.26
    
    -1.25
     sélectionné
    -1.24
     explosión
    -1.23
    POSITIVE LOGITS
     only
    2.25
     because
    1.90
     despite
    1.62
    because
    1.48
     although
    1.45
     just
    1.41
     but
    1.35
     ONLY
    1.30
     merely
    1.27
     Despite
    1.23
    Activations Density 0.168%

    No Known Activations