© 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. 112827
    Prev
    Next
    INDEX
    Explanations

    business advice or service

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

    traditionally cedar wood

    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
     Kal
    0.48
    ែង
    0.47
     Padma
    0.46
     Agn
    0.45
     Ç
    0.45
     Rö
    0.44
     Space
    0.44
     RPG
    0.44
     Desde
    0.44
     Ani
    0.44
    POSITIVE LOGITS
    unico
    0.47
    ವಾಗಿದೆ
    0.46
     کریں۔
    0.46
     धरना
    0.45
    口气
    0.45
     زیرمه
    0.45
     بیرون
    0.44
     संतुलन
    0.44
    क्रिप्शन
    0.43
    ።
    0.43
    Activations Density 0.002%

    No Known Activations