© 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. 60703
    Prev
    Next
    INDEX
    Explanations

    checking status or result

    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
    ингл
    -1.12
     déplo
    -1.09
    ándo
    -1.09
     lakier
    -1.01
     salaire
    -1.00
     todav
    -0.96
    ījum
    -0.95
     décret
    -0.95
     règlement
    -0.94
    biendo
    -0.93
    POSITIVE LOGITS
     success
    1.57
    success
    1.24
     error
    1.15
     successful
    1.14
     then
    1.14
     Success
    1.13
     "
    1.13
    ok
    1.13
    err
    1.12
     OK
    1.11
    Activations Density 0.004%

    No Known Activations