© 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. 45680
    Prev
    Next
    INDEX
    Explanations

    reports an ongoing action

    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
    4
    -2.77
    5
    -2.63
     a
    -2.63
     that
    -2.55
    8
    -2.50
    7
    -2.48
    3
    -2.41
    6
    -2.34
     when
    -2.25
    9
    -2.22
    POSITIVE LOGITS
     ")[
    1.86
    thenia
    1.79
     altres
    1.77
    dirond
    1.77
     juf
    1.73
    ícias
    1.72
     situe
    1.68
     Bajos
    1.67
     abonnement
    1.67
    ribute
    1.67
    Activations Density 0.316%

    No Known Activations