© 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. 10-GEMMASCOPE-RES-131K
    7. 57634
    Prev
    Next
    INDEX
    Explanations

    geographical area or region

    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
    ümüz
    -1.48
    蒾
    -1.30
    We
    -1.21
    </h5>
    -1.20
     innebär
    -1.17
    mě
    -1.16
     entraîner
    -1.16
    bės
    -1.16
     not
    -1.14
     }(\
    -1.13
    POSITIVE LOGITS
     area
    1.47
     ‘’
    1.17
     Bereichen
    1.17
     untill
    1.16
     createSprite
    1.13
     синий
    1.12
    =’
    1.11
     Plung
    1.10
     colla
    1.09
    контро
    1.09
    Activations Density 0.095%

    No Known Activations