© 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. 102075
    Prev
    Next
    INDEX
    Explanations

    quintessential descriptions

    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
    猻
    -2.53
    袮
    -2.52
     quando
    -2.41
    </i>
    -2.41
     aqueles
    -2.30
     üblichen
    -2.20
    薫
    -2.19
     tramite
    -2.17
     gesuchten
    -2.11
     Kiedy
    -2.11
    POSITIVE LOGITS
    ’
    2.59
     أيض
    2.53
    爻
    2.47
    靣
    2.34
    という感じ
    2.19
    囖
    2.13
     纳
    2.08
    辊
    2.05
    釓
    2.05
     fondamental
    2.03
    Activations Density 0.002%

    No Known Activations