© 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. 21160
    Prev
    Next
    INDEX
    Explanations

    algorithm or formula

    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
    ِل
    0.57
    tä
    0.57
     البطولة
    0.56
    
    0.56
    am
    0.53
    šku
    0.53
    mazione
    0.52
    َح
    0.52
    owied
    0.52
    ifrån
    0.52
    POSITIVE LOGITS
    י
    0.83
     of
    0.77
    Of
    0.73
    ।
    0.73
     purify
    0.72
    את
    0.69
     $\}$
    0.66
    б
    0.64
     that
    0.63
    カワ
    0.63
    Activations Density 0.000%

    No Known Activations