© 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. 34-GEMMASCOPE-RES-131K
    7. 108198
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
     this
    -1.45
     those
    -1.01
     where
    -1.00
     October
    -0.95
     choose
    -0.93
    狀況
    -0.88
     בשנת
    -0.87
     chose
    -0.86
     September
    -0.86
     July
    -0.85
    POSITIVE LOGITS
     horrid
    1.02
     Instrumente
    1.01
     durante
    1.01
     delightfully
    1.00
     exhilarating
    0.99
    telijke
    0.99
     exceedingly
    0.98
     alluring
    0.98
    cussion
    0.98
     outra
    0.95
    Activations Density 0.020%

    No Known Activations