© 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. 2779
    Prev
    Next
    INDEX
    Explanations

    do not, instead, yet, no

    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
     У
    0.24
    Config
    0.23
     Ме
    0.23
     Software
    0.22
    Proxy
    0.22
     ELISA
    0.22
     Config
    0.22
     E
    0.22
     S
    0.21
    新兴
    0.21
    POSITIVE LOGITS
     awfully
    0.31
     bothered
    0.28
     murderous
    0.28
     horribly
    0.28
     fondness
    0.27
     joking
    0.27
    ्तर
    0.27
     horrible
    0.27
    funny
    0.27
     horrors
    0.27
    Activations Density 0.482%

    No Known Activations