© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113957
    Prev
    Next
    INDEX
    Explanations

    specific entities or labels

    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
     especias
    -1.70
    hijab
    -1.66
     macetas
    -1.55
     Atmosphäre
    -1.46
    
    -1.45
     zostać
    -1.44
    Maw
    -1.41
     gebruiken
    -1.41
    UGHTER
    -1.38
     agrícola
    -1.37
    POSITIVE LOGITS
    Each
    1.76
    Specifically
    1.57
    Actually
    1.55
    Regardless
    1.46
    OP
    1.46
    with
    1.45
    TO
    1.45
    This
    1.45
    Only
    1.43
    Should
    1.42
    Activations Density 0.143%

    No Known Activations