© 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. 31-GEMMASCOPE-2-RES-262K
    7. 135234
    Prev
    Next
    INDEX
    Explanations

    videos or talks

    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_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ைக்கு
    0.46
    िर
    0.45
    머
    0.43
     (
    0.43
    有一些
    0.41
    (
    0.41
    inck
    0.40
    ，
    0.39
     privada
    0.39
    GetKey
    0.39
    POSITIVE LOGITS
    ╿
    0.52
    ט
    0.50
    ᐢ
    0.48
     दगडा
    0.46
     शकते
    0.45
     باشند
    0.45
     शकतात
    0.44
     Botanical
    0.44
     રે
    0.44
     Владимира
    0.44
    Activations Density 0.001%

    No Known Activations