© 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. 130110
    Prev
    Next
    INDEX
    Explanations

    describing research interests

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

    hitting major muscle groups

    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
     realtime
    0.45
    <0x80>
    0.43
    ik
    0.43
     ethereum
    0.42
    ంద్
    0.41
     वैसे
    0.40
    _
    0.39
    ๊
    0.39
    多久
    0.38
     สืบค้นเมื่อ
    0.38
    POSITIVE LOGITS
     ವಿದ್ಯ
    0.45
     contaminants
    0.45
     certifications
    0.45
     students
    0.44
     Associations
    0.44
    UTIONS
    0.44
    ÇÕES
    0.44
    謁
    0.43
     scorn
    0.43
     담당
    0.43
    Activations Density 0.005%

    No Known Activations