© 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. 207248
    Prev
    Next
    INDEX
    Explanations

    how to share information

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

    saving, ultimate source, research paper

    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
    盜
    0.53
     проблеми
    0.50
    מת
    0.49
    کم
    0.47
    jším
    0.47
    🎀
    0.47
    chodu
    0.47
    ……..
    0.47
    社長
    0.47
    驄
    0.46
    POSITIVE LOGITS
     άν
    0.47
     Tracks
    0.46
     Saving
    0.44
     ရှိ
    0.44
    တို့ကို
    0.43
     داریم
    0.43
     liền
    0.42
     Competition
    0.42
     Schools
    0.42
     Temple
    0.41
    Activations Density 0.001%

    No Known Activations