© 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. 52595
    Prev
    Next
    INDEX
    Explanations

    god, soul, strong, iris

    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
    로부터
    0.41
    inghouse
    0.40
    lic
    0.39
    პ
    0.39
    putes
    0.38
     tahap
    0.38
     കണ്ടെ
    0.38
    Ꮦ
    0.38
    criptor
    0.38
    Lic
    0.38
    POSITIVE LOGITS
     glasses
    0.40
     Which
    0.39
    ｑ
    0.39
     Working
    0.38
     Grayson
    0.38
    杉
    0.38
     pyramidal
    0.38
    囪
    0.38
    Apply
    0.38
     Alkali
    0.38
    Activations Density 0.003%

    No Known Activations