© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 84358
    Prev
    Next
    INDEX
    Explanations

    periods of time that include year

    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
     saurait
    -1.45
    FFIC
    -1.40
     санкт
    -1.38
     algunos
    -1.37
    遊んで
    -1.35
    楽しむ
    -1.33
    ticons
    -1.32
    苅
    -1.30
    řízení
    -1.30
     zví
    -1.28
    POSITIVE LOGITS
     the
    1.94
     you
    1.70
     your
    1.64
     it
    1.59
     that
    1.55
     in
    1.49
     tersebut
    1.47
    
    1.47
     anything
    1.47
     they
    1.44
    Activations Density 0.018%

    No Known Activations