© 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. 127922
    Prev
    Next
    INDEX
    Explanations

    acknowledgement followed by continuation

    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
     of
    -1.09
     by
    -1.05
     each
    -1.03
     ró
    -1.02
     such
    -1.01
    谙
    -1.01
     during
    -0.99
     every
    -0.98
     throughout
    -0.97
     in
    -0.96
    POSITIVE LOGITS
    総評
    1.19
     decidedly
    1.17
     now
    1.17
    🩱
    1.07
     jetzt
    1.01
    ildes
    1.00
     então
    0.99
    ☣
    0.98
     Himo
    0.97
     dilapidated
    0.97
    Activations Density 0.018%

    No Known Activations