© 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. 22-GEMMASCOPE-RES-131K
    7. 72427
    Prev
    Next
    INDEX
    Explanations

    promise goals guiding

    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
    Hanya
    -1.38
    Ketika
    -1.37
    Bagaimana
    -1.30
    Sebelum
    -1.28
    Kemudian
    -1.27
    Makanan
    -1.25
    Tetapi
    -1.24
     FORCES
    -1.23
    Это
    -1.21
    งิน
    -1.20
    POSITIVE LOGITS
     "
    1.64
     “
    1.46
     our
    1.41
     one
    1.29
     ‘
    1.28
     stated
    1.26
     the
    1.23
     what
    1.16
     all
    1.14
     of
    1.10
    Activations Density 0.017%

    No Known Activations