© 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. 112188
    Prev
    Next
    INDEX
    Explanations

    pronouns for people

    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
     neuen
    -1.77
    bbons
    -1.72
     for
    -1.63
    mitsub
    -1.62
     through
    -1.62
     with
    -1.52
     naszych
    -1.52
     on
    -1.52
    borsa
    -1.51
     nuestras
    -1.49
    POSITIVE LOGITS
     selve
    1.61
    1.57
     nacht
    1.53
     baden
    1.44
     stoff
    1.43
     geg
    1.41
    is
    1.40
     quelconque
    1.36
     schild
    1.36
     nimmer
    1.35
    Activations Density 0.117%

    No Known Activations