© 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-262K
    4. 52906
    Prev
    Next
    INDEX
    Explanations

    Java, Video, interface, starting

    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
     ব্যপারে
    0.43
    嗪
    0.42
     zéro
    0.42
    鿉
    0.42
     शिवसेने
    0.42
    捱
    0.42
    िलों
    0.42
     Vodafone
    0.41
     Swansea
    0.41
     తమి
    0.41
    POSITIVE LOGITS
    ber
    0.45
    berg
    0.45
    roid
    0.44
    ja
    0.43
    ly
    0.42
    opold
    0.41
    de
    0.40
    jo
    0.40
    $
    0.39
    ada
    0.39
    Activations Density 0.001%

    No Known Activations