© 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. 111947
    Prev
    Next
    INDEX
    Explanations

    university names

    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
    -
    -1.42
    拚
    -1.35
     proveniente
    -1.32
    證明
    -1.28
     there
    -1.28
    可能會
    -1.25
     etiquette
    -1.23
    旁边
    -1.22
     which
    -1.21
    驕
    -1.20
    POSITIVE LOGITS
    alanta
    1.55
    carnation
    1.48
    rages
    1.47
    棐
    1.45
    atürk
    1.45
     raisonnable
    1.45
    cursions
    1.42
    vertebrates
    1.42
    ciate
    1.41
    __*/
    1.41
    Activations Density 0.060%

    No Known Activations