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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71926
    Prev
    Next
    INDEX
    Explanations

    entity followed by "is a"

    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
    ︲
    -2.72
     raiſ
    -2.30
     of
    -2.28
    fe
    -2.25
    ts
    -2.00
     égard
    -1.98
    んびり
    -1.97
    ╿
    -1.97
    ."/
    -1.97
    つづく
    -1.97
    POSITIVE LOGITS
    軔
    2.30
    šinou
    2.14
     Проци
    2.11
     ungewöhn
    2.08
     beeindruck
    2.03
     merkwür
    2.03
     אנחנו
    2.02
     aparentemente
    2.00
    ㆆ
    1.99
     Durchmesser
    1.97
    Activations Density 0.003%

    No Known Activations