© 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. 59024
    Prev
    Next
    INDEX
    Explanations

    dorsal

    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
     collectons
    -2.78
     maquillage
    -2.61
     ſou
    -2.58
    ⵔ
    -2.56
    犴
    -2.55
    葶
    -2.52
    塍
    -2.48
    屙
    -2.47
    廛
    -2.44
     dangereux
    -2.42
    POSITIVE LOGITS
    A
    3.34
    with
    3.05
    ↵
    2.81
    However
    2.78
    With
    2.69
    .”
    2.55
    while
    2.50
    and
    2.44
    Only
    2.42
    an
    2.41
    Activations Density 0.012%

    No Known Activations