© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 40158
    Prev
    Next
    INDEX
    Explanations

    countries and states

    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
    ="
    -1.32
    /
    -1.31
     between
    -1.21
    の紹介
    -1.21
     from
    -1.20
     davvero
    -1.16
     realizzato
    -1.16
     to
    -1.15
     begleiten
    -1.14
     fattori
    -1.13
    POSITIVE LOGITS
     and
    1.44
    neous
    1.33
    ogues
    1.32
     etc
    1.31
    amerikan
    1.29
    rrrr
    1.26
    lllllll
    1.23
    thodoxy
    1.20
    termilk
    1.19
    llllll
    1.18
    Activations Density 0.029%

    No Known Activations