© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 7482
    Prev
    Next
    INDEX
    Explanations

    scoliosis and percentages

    np_acts-logits-general · gemini-2.5-flash-lite

    percentage and degree values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <unused75>
    0.50
    筷
    0.49
    子的
    0.49
    <unused78>
    0.49
     кош
    0.49
    <unused11>
    0.48
     автобу
    0.48
    加班
    0.47
    ijoje
    0.47
    西哥
    0.46
    POSITIVE LOGITS
     percentage
    1.05
     percent
    0.97
     percentages
    0.94
     Percent
    0.89
     percents
    0.87
     Percentage
    0.86
    percent
    0.85
     (%)
    0.84
    percentage
    0.82
     procent
    0.81
    Activations Density 0.012%

    No Known Activations