© 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. 193223
    Prev
    Next
    INDEX
    Explanations

    bookmark the permalink

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

    hydrolysis, solubility, bacteria

    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
    ם
    0.57
     ingenu
    0.49
     Parte
    0.47
    형
    0.47
    정
    0.46
     at
    0.46
     institucional
    0.46
    Settings
    0.46
     HEARING
    0.45
    ז
    0.45
    POSITIVE LOGITS
     بچوں
    0.46
     یونی
    0.45
    基督教
    0.44
     திரைப்பட
    0.44
     બાળકો
    0.44
     bactéries
    0.44
     Solubility
    0.43
     jotka
    0.43
    微生物
    0.43
     kinderen
    0.43
    Activations Density 0.005%

    No Known Activations