© 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. 113018
    Prev
    Next
    INDEX
    Explanations

    P-gp, algorithm, National Register

    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
    であるが
    -1.50
    可以直接
    -1.46
     mcqueen
    -1.45
     francès
    -1.45
    などは
    -1.42
     automne
    -1.40
     castel
    -1.38
     january
    -1.38
    to
    -1.38
     kroppen
    -1.34
    POSITIVE LOGITS
    actrice
    1.54
     who
    1.52
     and
    1.46
     welches
    1.41
     всѣ
    1.41
     they
    1.40
    }}}{\
    1.34
     sonre
    1.32
    cigarettes
    1.30
    裢
    1.28
    Activations Density 0.189%

    No Known Activations