© 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. 183179
    Prev
    Next
    INDEX
    Explanations

    knows/sees

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

    calculation, reading, daily usage

    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
    *
    0.57
    em
    0.49
    a
    0.47
    вил
    0.46
    ق
    0.45
    »
    0.45
    Yield
    0.43
    вила
    0.43
    existent
    0.43
    solve
    0.42
    POSITIVE LOGITS
     kennt
    0.55
     Kennt
    0.50
     লঞ্চ
    0.47
     对象
    0.47
     بیاکتنې
    0.47
     धार्मिक
    0.46
    婜
    0.45
     চিত্রক
    0.45
     বায়
    0.44
     जानना
    0.44
    Activations Density 0.000%

    No Known Activations