© 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. 45206
    Prev
    Next
    INDEX
    Explanations

    around-the-clock accessibility

    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
     has
    -1.43
     using
    -1.36
     ensuring
    -1.28
     where
    -1.27
     for
    -1.27
    Karriere
    -1.21
     just
    -1.18
     ALWAYS
    -1.17
     have
    -1.13
     some
    -1.13
    POSITIVE LOGITS
    especially
    1.50
    atized
    1.49
    这也是
    1.49
    mainly
    1.49
    </b>
    1.48
    particularly
    1.43
    again
    1.41
    arounds
    1.40
    atization
    1.38
    DataSetChanged
    1.38
    Activations Density 0.023%

    No Known Activations