© 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. 3210
    Prev
    Next
    INDEX
    Explanations

    font size specifications

    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
     emphasised
    0.44
     emphas
    0.42
     vó
    0.38
    YNAM
    0.38
    illery
    0.37
     enfat
    0.37
     dilat
    0.36
    鬍
    0.36
     vigorous
    0.36
    ຫຼ
    0.36
    POSITIVE LOGITS
    十二
    0.53
     ১২
    0.49
    Twelve
    0.49
     Twelve
    0.49
     Atlantic
    0.48
     Calibri
    0.47
     soup
    0.45
     fourteen
    0.44
     Soup
    0.44
    Atlantic
    0.44
    Activations Density 0.006%

    No Known Activations