© 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. 22-GEMMASCOPE-RES-131K
    7. 13931
    Prev
    Next
    INDEX
    Explanations

    company size

    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_22/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
     first
    -1.58
     for
    -1.47
     that
    -1.46
     because
    -1.35
     from
    -1.30
     even
    -1.28
     one
    -1.27
     might
    -1.24
     low
    -1.16
     not
    -1.13
    POSITIVE LOGITS
     who
    1.52
     vélos
    1.51
     célè
    1.48
     workforce
    1.46
     trabajan
    1.40
    𓆏
    1.36
     assurent
    1.35
     travaillent
    1.34
     πρ
    1.34
     magnific
    1.33
    Activations Density 0.020%

    No Known Activations