© 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. 45378
    Prev
    Next
    INDEX
    Explanations

    court document headers

    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
    Not in Any Lists

    No Comments

    Negative Logits
     his
    -2.27
     this
    -2.20
     When
    -2.14
     its
    -2.03
     seemingly
    -2.02
     time
    -1.92
     where
    -1.89
     our
    -1.82
     if
    -1.82
     M
    -1.82
    POSITIVE LOGITS
    itize
    2.66
    Ꮴ
    2.38
     noirs
    2.34
    arschu
    2.28
    eurs
    2.28
     neceſſ
    2.27
    dienne
    2.23
    AutoresizingMask
    2.22
    itisation
    2.22
    ឵
    2.20
    Activations Density 0.016%

    No Known Activations