© 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. 3594
    Prev
    Next
    INDEX
    Explanations

    programming variables and operations

    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
    郯
    0.45
    ньому
    0.43
    保安
    0.42
    SOUR
    0.42
    酚
    0.42
    ей
    0.41
    ENTES
    0.41
    Ꮙ
    0.41
    梼
    0.40
    úc
    0.40
    POSITIVE LOGITS
    _
    0.51
    ly
    0.45
     we
    0.40
     He
    0.40
     settlement
    0.40
    0.39
     determinants
    0.39
     mood
    0.38
     re
    0.38
     recur
    0.38
    Activations Density 0.217%

    No Known Activations