© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 47818
    Prev
    Next
    INDEX
    Explanations

    recursive variable n

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Minimize
    0.38
     transp
    0.38
     déploy
    0.38
    望着
    0.37
    ["
    0.37
    alinga
    0.37
    蘅
    0.37
     कुर
    0.36
    ượu
    0.36
     Materi
    0.36
    POSITIVE LOGITS
     glare
    0.45
    ^{-}\
    0.43
    isements
    0.41
     balances
    0.41
    ੇ
    0.41
    पुट
    0.40
     polish
    0.39
     जोड
    0.39
     উই
    0.39
    desk
    0.38
    Activations Density 0.002%

    No Known Activations