© 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. 67285
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and states

    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
    (
    -1.77
    5
    -1.69
    na
    -1.63
    "
    -1.55
    r
    -1.53
    th
    -1.53
    （
    -1.50
     it
    -1.49
    6
    -1.48
    v
    -1.46
    POSITIVE LOGITS
     to
    2.09
     until
    1.98
    mitsub
    1.97
     without
    1.90
     on
    1.82
     at
    1.79
     through
    1.60
    hijab
    1.60
    angkap
    1.59
     に関する
    1.57
    Activations Density 0.034%

    No Known Activations