© 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-262K
    7. 6141
    Prev
    Next
    INDEX
    Explanations

    explaining data points

    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
    PA
    0.52
    ES
    0.49
     Lernen
    0.46
    OMAS
    0.46
    PAUL
    0.46
    png
    0.46
    SB
    0.45
    Š
    0.45
    BA
    0.44
     produkty
    0.44
    POSITIVE LOGITS
    رى
    0.54
    ളാ
    0.48
    ssä
    0.47
    alay
    0.46
    usiasm
    0.45
    syair
    0.45
     yù
    0.45
    encji
    0.44
     ஆடி
    0.44
    ری
    0.43
    Activations Density 0.001%

    No Known Activations