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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60816
    Prev
    Next
    INDEX
    Explanations

    listing items separated by 'and'

    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
     wers
    -1.66
     vía
    -1.51
     sê
    -1.48
     toalla
    -1.48
     yii
    -1.48
    isait
    -1.48
    pso
    -1.45
    措施
    -1.42
     история
    -1.42
     ressemble
    -1.41
    POSITIVE LOGITS
    Also
    1.84
     ajudam
    1.81
     Also
    1.73
    Também
    1.65
     we
    1.63
     praktischen
    1.63
     أيضًا
    1.60
     універ
    1.59
     many
    1.57
     However
    1.52
    Activations Density 0.273%

    No Known Activations