© 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. 24941
    Prev
    Next
    INDEX
    Explanations

    errors or invalid states

    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
     from
    -1.53
     or
    -1.38
     one
    -1.22
     such
    -1.13
     when
    -1.11
     started
    -1.10
     using
    -1.10
     had
    -1.09
     for
    -1.09
     if
    -1.09
    POSITIVE LOGITS
     imposible
    1.05
     traseiro
    0.97
     ラウンド
    0.96
     etern
    0.94
    EXERC
    0.93
    INDUSTRY
    0.92
    ErrUnexpectedEOF
    0.92
     trasero
    0.92
     Mondo
    0.91
     errone
    0.91
    Activations Density 0.001%

    No Known Activations