© 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. 38328
    Prev
    Next
    INDEX
    Explanations

    HTML and XML structural elements

    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
     to
    -1.34
     referenced
    -1.30
     stolz
    -1.28
    蟜
    -1.27
    嫱
    -1.27
     whiteColor
    -1.20
    為に
    -1.19
    特意
    -1.16
    woke
    -1.16
     fastened
    -1.16
    POSITIVE LOGITS
    今は
    1.37
     staten
    1.31
     where
    1.23
     in
    1.23
    sieme
    1.22
    licitations
    1.22
     with
    1.16
    autorelease
    1.15
     tribunals
    1.12
    肫
    1.11
    Activations Density 0.002%

    No Known Activations