© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 98575
    Prev
    Next
    INDEX
    Explanations

    words transforming or not

    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
     chemically
    0.42
     gef
    0.42
    midnight
    0.38
     técn
    0.37
     remo
    0.37
     runat
    0.37
    できるように
    0.37
    凪
    0.37
     Tarn
    0.36
     BlogPost
    0.36
    POSITIVE LOGITS
    ponses
    0.45
    pti
    0.39
     हाउ
    0.38
    క్కు
    0.38
     কীভাবে
    0.38
     எவ்வாறு
    0.37
    ۖ
    0.37
     shapes
    0.37
    maligngroup
    0.37
     Responses
    0.36
    Activations Density 0.003%

    No Known Activations