© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 62333
    Prev
    Next
    INDEX
    Explanations

    stand by or stand out

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

    stands out

    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
    ből
    0.64
    넝
    0.61
    p
    0.61
    KER
    0.60
    لي
    0.60
    생활
    0.59
     আচ্ছা
    0.59
    $}
    0.59
    bab
    0.58
    ني
    0.57
    POSITIVE LOGITS
     Stand
    1.03
     berdiri
    1.01
     STAND
    1.00
     stand
    0.97
     खड़ा
    0.96
     debout
    0.96
     stood
    0.94
     standing
    0.92
     Standing
    0.89
     खड़े
    0.88
    Activations Density 0.037%

    No Known Activations