© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 53697
    Prev
    Next
    INDEX
    Explanations

    Her image, slide 2

    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
    ዊ
    0.44
     Abre
    0.43
     broaden
    0.41
     имен
    0.40
     Breite
    0.40
     expand
    0.38
     wid
    0.38
     latitude
    0.38
     sete
    0.38
    Isometric
    0.38
    POSITIVE LOGITS
    疹
    0.39
    Cook
    0.38
    Fight
    0.37
    चारियों
    0.36
    diag
    0.36
    แดง
    0.36
    Adam
    0.35
    መር
    0.35
    poruč
    0.35
    奀
    0.34
    Activations Density 0.001%

    No Known Activations