© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 36219
    Prev
    Next
    INDEX
    Explanations

    events occurring or described

    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
     徒歩
    -1.25
    uating
    -1.21
     sr
    -1.17
    actie
    -1.16
     spp
    -1.14
     exten
    -1.14
    atypes
    -1.13
     iti
    -1.13
    cked
    -1.12
     ont
    -1.12
    POSITIVE LOGITS
    =[]
    
    1.30
     you
    1.23
     that
    1.22
     menciona
    1.21
     celebró
    1.16
     of
    1.14
     confirmó
    1.11
    無論
    1.09
     poderá
    1.08
     registró
    1.08
    Activations Density 0.127%

    No Known Activations