© 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. 13538
    Prev
    Next
    INDEX
    Explanations

    about numbers and percentages

    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
     
    -1.44
     microfibra
    -1.27
     there
    -1.26
     этому
    -1.22
     been
    -1.22
    ్
    -1.21
     is
    -1.20
    这样的
    -1.16
     lavable
    -1.16
    reton
    -1.15
    POSITIVE LOGITS
     when
    2.52
     by
    1.77
     even
    1.77
     after
    1.76
     instead
    1.56
     for
    1.48
     in
    1.41
     before
    1.38
     only
    1.38
     if
    1.38
    Activations Density 0.087%

    No Known Activations