© 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. 63809
    Prev
    Next
    INDEX
    Explanations

    triggers, coax, Schedule B

    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
    Not in Any Lists

    No Comments

    Negative Logits
     života
    0.46
    鷹
    0.44
     Prez
    0.44
    |
    0.42
    餡
    0.41
     Ви
    0.40
     מדי
    0.40
     الاشتراك
    0.40
     США
    0.40
     holdings
    0.40
    POSITIVE LOGITS
     reacts
    0.45
     erinnert
    0.44
     cardiop
    0.43
     اهمیت
    0.43
     gud
    0.42
    偐
    0.42
     역할
    0.42
    las
    0.42
    穼
    0.41
     monocytes
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.