© 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. 92800
    Prev
    Next
    INDEX
    Explanations

    large datasets or ways

    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
     Breeze
    0.48
    ᱴ
    0.47
     पहनने
    0.46
     Poa
    0.46
     WhatsApp
    0.45
     really
    0.45
     telepon
    0.45
     Branco
    0.45
     Bangor
    0.45
     naprawdę
    0.45
    POSITIVE LOGITS
    به
    0.43
    зира
    0.41
    با
    0.41
     geeign
    0.41
     \;
    0.40
    umbia
    0.39
    cheidung
    0.39
    जागरण
    0.39
    化
    0.39
    א
    0.38
    Activations Density 0.007%

    No Known Activations