© 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. 22-GEMMASCOPE-RES-131K
    7. 64349
    Prev
    Next
    INDEX
    Explanations

    prefixes forming words

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     shimmering
    -1.52
     exhilarating
    -1.44
    !!!!!!!
    -1.44
    A
    -1.38
     opulent
    -1.37
    L
    -1.36
    {\
    -1.35
     avancé
    -1.34
    R
    -1.34
    T
    -1.33
    POSITIVE LOGITS
     this
    1.78
     and
    1.75
     before
    1.57
     both
    1.55
    Kuva
    1.54
     when
    1.53
     mencegah
    1.53
     while
    1.52
     during
    1.51
     because
    1.45
    Activations Density 0.044%

    No Known Activations