© 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. 95354
    Prev
    Next
    INDEX
    Explanations

    people's jobs and roles

    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
    :
    -1.34
    ing
    -1.14
    G
    -1.07
    !
    -1.05
    w
    -1.05
    &
    -1.04
    N
    -1.03
    f
    -1.03
    IO
    -1.02
    !!!!
    -1.01
    POSITIVE LOGITS
    ſſen
    1.23
     dichter
    1.17
     kulinar
    1.16
     gustaMe
    1.15
    uccess
    1.13
     vœux
    1.13
    तीय
    1.09
     kontro
    1.09
     lavable
    1.08
     amortigu
    1.07
    Activations Density 0.495%

    No Known Activations