© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 112000
    Prev
    Next
    INDEX
    Explanations

    css/code structure

    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
     cyanide
    0.54
     radioactive
    0.51
     atuação
    0.50
     ラ
    0.49
     ⿱
    0.49
    ък
    0.49
     ត
    0.49
     църква
    0.49
     resuspended
    0.48
     mountainous
    0.47
    POSITIVE LOGITS
    RO
    0.57
    USA
    0.50
     senc
    0.46
     handels
    0.46
    PO
    0.45
    p
    0.44
     istot
    0.44
    STR
    0.44
     oman
    0.44
    KH
    0.43
    Activations Density 0.002%

    No Known Activations