© 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. 16-GEMMASCOPE-2-RES-262K
    7. 12906
    Prev
    Next
    INDEX
    Explanations

    multilingual factual information

    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_16_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
    й
    0.55
     exacting
    0.54
    이
    0.53
    ка
    0.52
    レ
    0.52
    ین
    0.51
    은
    0.51
    and
    0.50
    ری
    0.49
    CRETE
    0.48
    POSITIVE LOGITS
     feito
    0.57
     Матери
    0.56
            
    0.53
    ligt
    0.53
     Когда
    0.52
    S
    0.52
     પાણી
    0.52
     mensen
    0.51
     branco
    0.51
    ódio
    0.50
    Activations Density 0.021%

    No Known Activations