© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12444
    Prev
    Next
    INDEX
    Explanations

    exception and error types

    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
     Synag
    -1.52
    Ď
    -1.28
     condicionado
    -1.26
     rústico
    -1.21
    苹果
    -1.20
     doméstico
    -1.20
     pensado
    -1.20
     pesado
    -1.19
    圣节
    -1.18
     animado
    -1.17
    POSITIVE LOGITS
    0
    2.25
    8
    2.13
    3
    2.13
    4
    2.08
    5
    2.02
     since
    1.81
    2
    1.75
     because
    1.73
    6
    1.73
     puisqu
    1.70
    Activations Density 0.004%

    No Known Activations