© 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. 113654
    Prev
    Next
    INDEX
    Explanations

    knowledge base documents databases FAQs

    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
    法國
    0.45
     наказа
    0.41
     пере
    0.40
    ল
    0.40
    го
    0.40
    폐
    0.39
    пель
    0.39
     examination
    0.38
     Fransiya
    0.38
     }^{*}
    0.37
    POSITIVE LOGITS
    s
    0.50
     eignet
    0.46
    idey
    0.46
     ohmic
    0.45
    ämä
    0.45
    Typical
    0.44
    足够
    0.43
     идеи
    0.43
    ignent
    0.42
     Kudos
    0.42
    Activations Density 0.006%

    No Known Activations