© 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. 14483
    Prev
    Next
    INDEX
    Explanations

    an article indicator

    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
    0
    -3.89
    2
    -2.86
    3
    -2.80
     Quando
    -2.64
    5
    -2.58
    4
    -2.53
     rilass
    -2.45
     ángulo
    -2.39
    7
    -2.38
    o
    -2.36
    POSITIVE LOGITS
    鯪
    2.88
    玗
    2.83
    鋮
    2.73
     enormous
    2.61
     exquisitely
    2.59
     sizable
    2.59
    ꠥ
    2.56
    ?’
    2.55
    龊
    2.48
    )";
    2.45
    Activations Density 0.007%

    No Known Activations