© 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. 99859
    Prev
    Next
    INDEX
    Explanations

    proper use or way

    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
     '
    -3.34
     dando
    -3.03
     famoso
    -3.02
     bizarre
    -2.75
     tomando
    -2.73
     marvelous
    -2.73
     "
    -2.70
     magnificent
    -2.69
     turmoil
    -2.66
    (
    -2.64
    POSITIVE LOGITS
    Although
    3.77
    Surprisingly
    3.73
    Even
    3.53
    Some
    3.50
    0
    3.44
    While
    3.42
    Despite
    3.42
     Surprisingly
    3.39
    Several
    3.33
    Though
    3.31
    Activations Density 0.011%

    No Known Activations