© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 15057
    Prev
    Next
    INDEX
    Explanations

    expecting future actions

    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
     more
    -1.91
     either
    -1.87
     what
    -1.80
     already
    -1.73
     only
    -1.73
     you
    -1.70
     transférez
    -1.67
     could
    -1.63
     on
    -1.63
     уже
    -1.62
    POSITIVE LOGITS
     هیچ
    1.56
    \'{
    1.45
     OCTOBER
    1.45
     artykuł
    1.44
     zaman
    1.44
     quatre
    1.41
    ATION
    1.40
     SCOTT
    1.38
    folge
    1.38
     mijn
    1.38
    Activations Density 0.013%

    No Known Activations