© 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. 70134
    Prev
    Next
    INDEX
    Explanations

    hand or current

    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
     it
    -1.84
     or
    -1.73
    它
    -1.63
    It
    -1.59
    OREM
    -1.53
    Just
    -1.49
    它的
    -1.45
     DELLE
    -1.45
    There
    -1.44
     through
    -1.43
    POSITIVE LOGITS
     is
    1.70
     actuellement
    1.69
     actualmente
    1.66
     atualmente
    1.49
     คือ
    1.49
     a
    1.48
     ส
    1.47
     soldat
    1.47
    ྃ
    1.46
     เร
    1.45
    Activations Density 0.195%

    No Known Activations