© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60654
    Prev
    Next
    INDEX
    Explanations

    earlier events and references

    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
     eerste
    -1.59
    釭
    -1.58
     is
    -1.47
     diseñada
    -1.43
     to
    -1.38
     inklusive
    -1.33
    aabb
    -1.31
    𖣔
    -1.31
     pública
    -1.30
    zapatilla
    -1.30
    POSITIVE LOGITS
     earlier
    1.86
    $*$
    1.85
    
    1.73
     Earlier
    1.70
     brancas
    1.66
    AutoresizingMask
    1.61
     晚
    1.55
    笮
    1.52
    quela
    1.52
     garagem
    1.52
    Activations Density 0.016%

    No Known Activations