© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220972
    Prev
    Next
    INDEX
    Explanations

    variable bindings in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ที่เรา
    0.67
    ที่
    0.55
    ທີ່
    0.47
    ที่คุณ
    0.45
    టువంటి
    0.44
     என்னுடைய
    0.43
    ที่จะ
    0.42
    ﮭ
    0.42
     که
    0.42
    हरूको
    0.42
    POSITIVE LOGITS
     they
    0.76
     she
    0.62
     we
    0.57
    they
    0.53
     вона
    0.50
     તેઓ
    0.47
     you
    0.46
     তারা
    0.44
     они
    0.43
     त्यांनी
    0.43
    Activations Density 0.005%

    No Known Activations