© 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. 68492
    Prev
    Next
    INDEX
    Explanations

    proxy declarations

    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
     who
    -1.52
     unless
    -1.52
    炻
    -1.32
    웠
    -1.23
     может
    -1.23
    Clima
    -1.23
    immen
    -1.22
     that
    -1.21
    sätzlich
    -1.20
     they
    -1.20
    POSITIVE LOGITS
     「
    1.55
    ments
    1.36
    rm
    1.33
    xically
    1.29
    It
    1.26
    de
    1.25
    av
    1.25
    brania
    1.24
    urs
    1.21
    ING
    1.21
    Activations Density 0.005%

    No Known Activations