© 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. 73547
    Prev
    Next
    INDEX
    Explanations

    status and success indicators

    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
     פשוט
    -0.94
     signifikan
    -0.91
    Etimología
    -0.90
    ворю
    -0.90
    TERY
    -0.88
    AtEndOf
    -0.88
     annan
    -0.88
     bayi
    -0.87
    Με
    -0.85
     lavage
    -0.84
    POSITIVE LOGITS
     OK
    2.23
     ok
    2.16
     success
    2.14
    OK
    2.09
     okay
    2.03
    ok
    1.82
    success
    1.71
     Okay
    1.55
     sucesso
    1.53
    Ok
    1.50
    Activations Density 0.030%

    No Known Activations