© 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. 72578
    Prev
    Next
    INDEX
    Explanations

    events and concluding statements

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

    substance, startup, distributor

    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
    Theorem
    0.47
    NCc
    0.45
    TimeDict
    0.45
    CDCl
    0.44
    惧
    0.44
     cancelación
    0.44
    ổ
    0.44
     subdue
    0.43
    FreeBuf
    0.43
     ক্ষত্রিয়
    0.43
    POSITIVE LOGITS
     Aurora
    0.40
    imon
    0.39
    оны
    0.39
    杭州
    0.38
     replicated
    0.38
    رف
    0.38
    ,
    0.38
     Advanced
    0.37
     scarring
    0.37
     Monsoon
    0.37
    Activations Density 0.000%

    No Known Activations