© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4035
    Prev
    Next
    INDEX
    Explanations

    method or type conversion

    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
    Not in Any Lists

    No Comments

    Negative Logits
     these
    -1.80
     and
    -1.66
     those
    -1.65
     because
    -1.59
     by
    -1.47
     &
    -1.47
     now
    -1.47
     other
    -1.46
     at
    -1.45
     through
    -1.44
    POSITIVE LOGITS
     rigue
    1.57
     tâches
    1.56
     icônes
    1.52
     juſ
    1.52
    薷
    1.46
     papiers
    1.42
     aéri
    1.41
     erreurs
    1.41
     cérami
    1.38
     leſs
    1.38
    Activations Density 0.024%

    No Known Activations