© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 40430
    Prev
    Next
    INDEX
    Explanations

    sequences like 10 or 12

    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
     is
    -2.09
     of
    -1.51
     would
    -1.45
     will
    -1.37
     also
    -1.34
     from
    -1.31
     into
    -1.28
     should
    -1.21
     gave
    -1.18
     eight
    -1.18
    POSITIVE LOGITS
     potenci
    1.62
     jener
    1.34
     biedt
    1.30
     nede
    1.30
    comes
    1.29
    젬
    1.27
    rfan
    1.26
    Budapest
    1.26
    ḿ
    1.25
     BIRTHDAY
    1.24
    Activations Density 0.046%

    No Known Activations