© 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. 31-GEMMASCOPE-2-RES-262K
    7. 110978
    Prev
    Next
    INDEX
    Explanations

    grab attention

    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_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
     Bat
    0.51
     de
    0.50
     o
    0.48
    Bat
    0.47
     Πα
    0.47
    d
    0.45
     Nej
    0.44
    o
    0.44
     polic
    0.44
    кий
    0.44
    POSITIVE LOGITS
    tFileInputExcel
    0.48
     rebates
    0.48
    ittings
    0.48
     비용
    0.47
     کرنا
    0.46
    punctuation
    0.45
    opub
    0.45
    UMO
    0.45
    ETA
    0.45
     श्रॉफ
    0.45
    Activations Density 0.002%

    No Known Activations