© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12132
    Prev
    Next
    INDEX
    Explanations

    look at or followed by verb

    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
    ,
    -2.45
    {
    -1.81
     us
    -1.80
    -
    -1.77
     you
    -1.73
     if
    -1.72
     my
    -1.68
     our
    -1.35
     be
    -1.34
     podemos
    -1.32
    POSITIVE LOGITS
     propter
    1.61
    romatic
    1.60
     annuel
    1.53
     ***!
    1.51
     obb
    1.49
     matrice
    1.41
    )");
    1.40
     pecuni
    1.40
     brevis
    1.40
     hect
    1.38
    Activations Density 0.073%

    No Known Activations