© 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-65K
    7. 53248
    Prev
    Next
    INDEX
    Explanations

    relating words or descriptions

    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
    collapsed
    0.41
    hut
    0.40
     bina
    0.40
    ̎
    0.39
     ciem
    0.38
     liu
    0.38
     Rochelle
    0.37
     dubai
    0.37
     unfolds
    0.36
    bleau
    0.36
    POSITIVE LOGITS
    ంతో
    0.50
     относится
    0.47
     ಈಗಾಗಲೇ
    0.47
    因為
    0.46
     относя
    0.45
    ênio
    0.44
     eminently
    0.44
    责
    0.43
    ösen
    0.43
     ضرور
    0.43
    Activations Density 0.048%

    No Known Activations