© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 9537
    Prev
    Next
    INDEX
    Explanations

    non-green evaporation or binds to

    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
    Negative Logits
    hyperref
    0.49
     დღ
    0.45
    ODBA
    0.41
    パッケージ
    0.40
     হাইক
    0.40
    ภูมิ
    0.39
    啖
    0.38
    編曲
    0.37
    もあり
    0.37
    ០
    0.37
    POSITIVE LOGITS
     Environment
    0.41
     experienced
    0.40
     preference
    0.40
     machine
    0.39
    hend
    0.39
    unsqueeze
    0.39
    ल्फ
    0.38
     [+]
    0.38
    مي
    0.38
    getLocal
    0.37
    Activations Density 0.000%

    No Known Activations