© 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. 58530
    Prev
    Next
    INDEX
    Explanations

    asking how to

    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
    3
    -2.36
    9
    -2.28
    先是
    -1.99
    8
    -1.95
    6
    -1.93
    2
    -1.89
    4
    -1.89
    1
    -1.86
    {
    -1.84
    我希望
    -1.79
    POSITIVE LOGITS
     and
    2.27
    梘
    2.00
     ddelwed
    1.87
     canad
    1.84
     dimensi
    1.75
     from
    1.72
    咐
    1.72
    幛
    1.70
    ꔹ
    1.70
     legislat
    1.69
    Activations Density 0.048%

    No Known Activations