© 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-65K
    4. 3306
    Prev
    Next
    INDEX
    Explanations

    descriptive words and their resulting category

    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_65k_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
     ఎక్కువ
    0.43
     ομά
    0.42
     {});
    0.38
     {\
    0.38
    |,
    0.37
    setObjectName
    0.36
     toDo
    0.36
     various
    0.35
    )$.
    0.35
     জীবন
    0.35
    POSITIVE LOGITS
    -
    0.57
     olmayan
    0.50
    ترین
    0.46
     ترین
    0.46
    ‌ترین
    0.43
     ومع
    0.42
     eksempel
    0.42
    ۷
    0.42
    issime
    0.42
     exempel
    0.41
    Activations Density 0.272%

    No Known Activations