© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-RES-262K
    7. 64269
    Prev
    Next
    INDEX
    Explanations

    which introduces a requirement

    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_53_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
     что
    0.45
     doppio
    0.42
    aVal
    0.41
     ತೋರಿಸ
    0.41
    <<<
    0.41
     სპეცი
    0.40
     পোস্টে
    0.40
     सहमत
    0.40
     ২০১৫
    0.40
    ীবনী
    0.40
    POSITIVE LOGITS
     which
    0.57
    which
    0.55
     mely
    0.54
     skall
    0.53
     والذي
    0.51
     welcher
    0.50
     quale
    0.49
    ซึ่ง
    0.49
    及
    0.47
     οποία
    0.46
    Activations Density 0.005%

    No Known Activations