© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 172933
    Prev
    Next
    INDEX
    Explanations

    appreciate like want

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

    seeing where

    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
    দ
    0.53
    疠
    0.46
     shipments
    0.46
    硗
    0.45
    ن
    0.44
    យើង
    0.44
    ధ
    0.44
    ન
    0.43
    ദ
    0.43
    鳅
    0.43
    POSITIVE LOGITS
     Caro
    0.48
     baru
    0.48
     Cora
    0.46
     पुस्त
    0.45
    zaam
    0.45
     Membuat
    0.44
     Haas
    0.43
     Baru
    0.43
    ,​
    0.43
    ivität
    0.43
    Activations Density 0.001%

    No Known Activations