© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211928
    Prev
    Next
    INDEX
    Explanations

    specific words

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

    reusable, replacement, framework, impact

    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
    Negative Logits
    價
    0.58
    ν
    0.54
     συγκεκρι
    0.48
    爀
    0.48
    triggers
    0.47
    單位
    0.45
    真的
    0.45
    都是
    0.44
    田
    0.44
    रोला
    0.43
    POSITIVE LOGITS
    ünü
    0.50
     Hein
    0.48
     Tä
    0.48
     Technical
    0.47
     അയ
    0.47
    czę
    0.46
    Hein
    0.46
     yet
    0.46
     denaturation
    0.45
     তথাপি
    0.45
    Activations Density 0.000%

    No Known Activations