© 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. 64606
    Prev
    Next
    INDEX
    Explanations

    Polysaccharides, Congenital, Founded

    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
    Not in Any Lists

    No Comments

    Negative Logits
     ilumina
    -1.29
     touché
    -1.20
     drapeau
    -1.18
     sorprende
    -1.16
     contraire
    -1.16
    Ꮴ
    -1.13
     unless
    -1.10
    皷
    -1.09
     documentaire
    -1.09
     aussit
    -1.09
    POSITIVE LOGITS
     had
    1.06
    C
    1.02
    cześ
    1.01
    k
    1.01
    Very
    1.00
    on
    0.99
    more
    0.99
    David
    0.99
    AL
    0.98
    AA
    0.98
    Activations Density 0.001%

    No Known Activations