© 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. 41-GEMMASCOPE-2-RES-262K
    7. 34187
    Prev
    Next
    INDEX
    Explanations

    provider, channel, sum

    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_all/layer_41_width_262k_l0_big
    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
     ಪ್ಯಾ
    0.44
     Weighted
    0.42
     releasing
    0.39
     rollout
    0.39
    膈
    0.39
     sponsorship
    0.39
     Releases
    0.39
    ྵ
    0.39
    リック
    0.38
     ಮಹಿ
    0.38
    POSITIVE LOGITS
    wirkung
    0.39
     junction
    0.39
     wo
    0.38
    pressed
    0.38
    id
    0.37
    нос
    0.37
     এক্সপ্রেস
    0.37
    spre
    0.37
     Junction
    0.37
     tel
    0.37
    Activations Density 0.001%

    No Known Activations