© 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. 172092
    Prev
    Next
    INDEX
    Explanations

    written warning, maintain appropriate, be called

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

    science and business terms

    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
    见面
    0.46
     misch
    0.46
    揉
    0.46
    న్నా
    0.45
    })^{\
    0.45
    乐队
    0.45
    鷳
    0.45
    懷
    0.45
     Кра
    0.44
     аба
    0.44
    POSITIVE LOGITS
     pharmacology
    0.51
     microarray
    0.44
     PubMed
    0.43
     Burlington
    0.43
     pharmacological
    0.43
     biennium
    0.42
     nią
    0.42
    NetAmount
    0.42
     r
    0.41
     undergraduate
    0.41
    Activations Density 0.001%

    No Known Activations