© 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. 185252
    Prev
    Next
    INDEX
    Explanations

    remodel the basement

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

    partnering with, API Documentation, Product Category, ML working, Temporary Increased, touching on, Guitar, Levels often

    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
     اداروں
    0.48
    鰯
    0.45
     சரி
    0.45
    িতেছি
    0.44
    चिंत
    0.44
    localVar
    0.43
    กิจกรรม
    0.43
    LoginActivity
    0.42
    ꗥ
    0.42
     পালিয়ে
    0.42
    POSITIVE LOGITS
     بهذه
    0.47
     audacity
    0.45
     بهذا
    0.43
     بالف
    0.42
     specifico
    0.42
     тут
    0.41
     избра
    0.41
     avenue
    0.40
    이는
    0.40
     أك
    0.40
    Activations Density 0.001%

    No Known Activations