© 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. 8431
    Prev
    Next
    INDEX
    Explanations

    sign and polarity

    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
    Negative Logits
    ]}$
    -1.97
     Other
    -1.94
    derdag
    -1.82
     Not
    -1.82
     When
    -1.81
     Only
    -1.80
     We
    -1.79
     In
    -1.79
    (
    -1.78
     Another
    -1.77
    POSITIVE LOGITS
     of
    2.33
    2
    2.11
     menyen
    1.85
    または
    1.82
    有点
    1.82
     袖
    1.80
     parfü
    1.80
    4
    1.76
    wendige
    1.76
     konstant
    1.74
    Activations Density 0.009%

    No Known Activations