© 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. 31-GEMMASCOPE-2-RES-65K
    7. 9319
    Prev
    Next
    INDEX
    Explanations

    comments explaining code

    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_31_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
     niacin
    0.58
     results
    0.57
     उर्फी
    0.57
     can
    0.56
    âce
    0.54
     modals
    0.54
    า
    0.54
     isoforms
    0.53
     stellt
    0.53
     cairan
    0.53
    POSITIVE LOGITS
    is
    0.59
    w
    0.56
    z
    0.53
    el
    0.50
    P
    0.50
    注释
    0.48
    мента
    0.48
    et
    0.48
    mark
    0.47
    пе
    0.47
    Activations Density 0.023%

    No Known Activations