© 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. 108863
    Prev
    Next
    INDEX
    Explanations

    create different text formats

    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
    은
    0.57
    프트
    0.52
    Hence
    0.50
     무엇
    0.47
    hence
    0.47
    joint
    0.46
    Prep
    0.46
     vinto
    0.46
    finite
    0.46
    ި
    0.46
    POSITIVE LOGITS
     cac
    0.52
     SKU
    0.51
     LGBTQ
    0.47
     KSI
    0.47
     CAC
    0.45
     Gabriella
    0.45
     ऑक्स
    0.45
     Alexis
    0.45
     CTV
    0.45
     Bobcats
    0.43
    Activations Density 0.001%

    No Known Activations