© 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. 71286
    Prev
    Next
    INDEX
    Explanations

    children imitating father

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

    focus on future

    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
     결
    0.47
    结
    0.42
     erode
    0.41
     izvr
    0.40
     yı
    0.39
     rein
    0.38
     keep
    0.38
     Conclusion
    0.38
     Mez
    0.38
     vele
    0.38
    POSITIVE LOGITS
    クサ
    0.46
    下に
    0.42
    டுகளில்
    0.41
    ޏ
    0.41
    日本では
    0.40
    lardan
    0.39
    Veg
    0.39
    σουν
    0.39
     তখন
    0.38
    最初の
    0.38
    Activations Density 0.006%

    No Known Activations