© 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. 34-GEMMASCOPE-RES-131K
    7. 119099
    Prev
    Next
    INDEX
    Explanations

    package names and imports

    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
     availa
    -0.75
     ecclesias
    -0.71
     Далее
    -0.69
    ៀ
    -0.69
     Более
    -0.66
     traverser
    -0.66
    Audiences
    -0.65
     REVIEWS
    -0.65
    شف
    -0.65
    рный
    -0.65
    POSITIVE LOGITS
     Sys
    1.23
     sys
    1.21
    sys
    1.20
    Dict
    1.20
     Dict
    1.13
    Sys
    1.11
    Role
    1.08
    User
    1.02
     User
    1.02
    basicConfig
    0.97
    Activations Density 0.009%

    No Known Activations