© 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. 4016
    Prev
    Next
    INDEX
    Explanations

    what, how, why

    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
    آ
    0.33
    𝚑
    0.33
     ያለ
    0.33
    kowych
    0.31
    haviours
    0.31
     오히려
    0.30
     आर्थिक
    0.30
    ਤ
    0.30
    眈
    0.30
    理由は
    0.30
    POSITIVE LOGITS
     eg
    0.32
     begins
    0.31
    Eg
    0.31
     maximizes
    0.30
     bzw
    0.30
     bevel
    0.29
    0.29
    lib
    0.29
     Specifies
    0.29
     connects
    0.29
    Activations Density 0.097%

    No Known Activations