© 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. 68332
    Prev
    Next
    INDEX
    Explanations

    discretionary judgment

    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
     Anſ
    -1.49
     niks
    -1.47
    çons
    -1.44
     cárcel
    -1.40
    ciale
    -1.40
     irmãos
    -1.39
    閙
    -1.38
    piele
    -1.38
     ſeveral
    -1.35
    🍬
    -1.35
    POSITIVE LOGITS
    7
    2.08
    6
    1.91
    0
    1.88
    G
    1.76
    8
    1.75
     if
    1.72
    5
    1.63
    A
    1.62
    3
    1.60
    9
    1.59
    Activations Density 0.029%

    No Known Activations