© 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. 213274
    Prev
    Next
    INDEX
    Explanations

    punch

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

    constraint, Predict, again, space, unilateral, vr

    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
    िंग्स
    0.52
     cuarto
    0.48
    ლ
    0.47
     publie
    0.47
     Öffentlich
    0.46
    公开
    0.45
    প
    0.45
    𝐏
    0.45
     सार्वजनिक
    0.44
    公開
    0.44
    POSITIVE LOGITS
     ለማ
    0.50
     ರಾಜ್ಯ
    0.49
    ional
    0.48
    ime
    0.46
    akas
    0.46
    czy
    0.46
     executes
    0.46
     გას
    0.45
    gae
    0.44
     زیادی
    0.44
    Activations Density 0.000%

    No Known Activations