© 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-262K
    7. 28816
    Prev
    Next
    INDEX
    Explanations

    backup with, testing the, delete directories

    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_262k_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
    ̰
    0.39
    ະ
    0.38
    ᱘
    0.37
     पाठ्यक्रम
    0.35
     multiplicar
    0.35
    न्ड
    0.34
    °)
    0.33
    န်
    0.33
     TA
    0.33
     unlawful
    0.33
    POSITIVE LOGITS
     against
    0.52
    against
    0.43
     with
    0.42
     AGAINST
    0.41
    ene
    0.40
     چیز
    0.39
     terhadap
    0.39
     Against
    0.39
     iets
    0.39
     into
    0.38
    Activations Density 0.031%

    No Known Activations