© 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. 34-GEMMASCOPE-RES-131K
    7. 47022
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and specific contexts

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Was
    -0.82
    ica
    -0.81
     PA
    -0.81
    ern
    -0.80
     Care
    -0.79
    Ra
    -0.78
    ra
    -0.77
    ens
    -0.77
    ance
    -0.77
    pa
    -0.76
    POSITIVE LOGITS
    warted
    0.89
     diskon
    0.88
    ==",
    0.87
    illés
    0.86
     Saltar
    0.83
    بیل
    0.83
    seamnă
    0.83
     annealed
    0.82
    瓴
    0.81
     APPEAL
    0.80
    Activations Density 0.037%

    No Known Activations