© 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. 20612
    Prev
    Next
    INDEX
    Explanations

    names and titles

    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
     of
    -1.80
     to
    -1.52
     even
    -1.36
     if
    -1.11
     how
    -1.02
    叽
    -1.02
     him
    -1.01
     help
    -1.01
     either
    -1.00
    rąg
    -1.00
    POSITIVE LOGITS
     semacam
    1.34
     нашей
    1.23
    such
    1.23
     relojes
    1.19
     anillos
    1.18
     juguetes
    1.18
     такие
    1.18
     takie
    1.16
    岡山
    1.16
     mantuvo
    1.16
    Activations Density 0.187%

    No Known Activations