© 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. 10-GEMMASCOPE-RES-131K
    7. 101037
    Prev
    Next
    INDEX
    Explanations

    formulas for calculation

    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
     ‚
    -1.77
     specif
    -1.63
     procedimientos
    -1.61
    extremely
    -1.60
    
    -1.59
    guarantee
    -1.58
    튿
    -1.57
    </strong>
    -1.56
     unbelievably
    -1.55
     innumer
    -1.55
    POSITIVE LOGITS
     any
    2.44
     for
    2.41
     two
    2.23
     if
    2.22
     all
    2.06
     three
    2.06
     at
    2.03
     by
    2.03
     an
    2.00
     just
    1.95
    Activations Density 0.076%

    No Known Activations