© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 92414
    Prev
    Next
    INDEX
    Explanations

    how things work

    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
    騫
    0.48
    動
    0.46
    換
    0.46
    字
    0.44
    움
    0.43
    の発
    0.42
     Daerah
    0.41
    в
    0.41
     crawling
    0.41
     setempat
    0.40
    POSITIVE LOGITS
    ir
    0.58
    utada
    0.57
    jede
    0.52
    জাতি
    0.48
    ان
    0.48
    narr
    0.48
    inform
    0.47
    jó
    0.47
     honoured
    0.47
    an
    0.46
    Activations Density 0.003%

    No Known Activations