© 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. 90392
    Prev
    Next
    INDEX
    Explanations

    thing to verb

    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
    ↵↵
    -2.09
    
    -1.99
     maleta
    -1.85
     playera
    -1.85
    𞤢
    -1.77
    妧
    -1.76
     pulsera
    -1.74
     botines
    -1.73
     chaqueta
    -1.68
    ܧ
    -1.64
    POSITIVE LOGITS
     to
    6.03
    bermuda
    1.79
     will
    1.60
     for
    1.58
    又は
    1.56
    utched
    1.55
    orice
    1.55
     deberán
    1.53
     welchem
    1.53
    uese
    1.53
    Activations Density 0.110%

    No Known Activations