© 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-262K
    7. 2176
    Prev
    Next
    INDEX
    Explanations

    phrasal verbs or definitions

    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
    redi
    0.49
    ley
    0.49
    red
    0.48
    illen
    0.46
    تور
    0.46
    깍
    0.46
    ുകെ
    0.45
    iav
    0.44
    고
    0.44
    놀
    0.44
    POSITIVE LOGITS
    сюда
    0.48
     Tattha
    0.44
     करतात
    0.43
    Goodbye
    0.43
     totality
    0.42
     दिस
    0.42
     needing
    0.42
    暐
    0.41
     requiring
    0.41
    Uns
    0.41
    Activations Density 0.000%

    No Known Activations