© 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. 73617
    Prev
    Next
    INDEX
    Explanations

    father, dad, brother

    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
    ŗ
    -1.30
     Sänger
    -1.13
     продолжа
    -1.13
     utiliser
    -1.13
     {
    -1.11
     tatou
    -1.11
    ऐ
    -1.09
    のための
    -1.09
     儿
    -1.08
     usar
    -1.06
    POSITIVE LOGITS
     with
    1.59
     machten
    1.30
    在她
    1.26
     yılında
    1.23
     without
    1.21
    0
    1.19
    他知道
    1.17
     Wartawan
    1.15
    鯔
    1.14
    PUESTA
    1.13
    Activations Density 0.058%

    No Known Activations