© 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. 112972
    Prev
    Next
    INDEX
    Explanations

    around or sitting

    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
    摸了
    -1.61
    えている
    -1.60
    看了一眼
    -1.51
    并在
    -1.48
    are
    -1.48
    相変わらず
    -1.47
     حدود
    -1.46
    躋
    -1.46
     rams
    -1.44
    4
    -1.44
    POSITIVE LOGITS
     for
    2.22
    垕
    1.55
     an
    1.49
     insanların
    1.48
     a
    1.46
     Mě
    1.44
    panjang
    1.41
     decreases
    1.38
    lux
    1.38
     When
    1.38
    Activations Density 0.011%

    No Known Activations