© 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-65K
    7. 8450
    Prev
    Next
    INDEX
    Explanations

    PHP defined('constant') checks

    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_65k_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
    Greek
    0.52
     Greek
    0.50
     ))}
    0.49
    >-->
    0.44
    říklad
    0.43
    greater
    0.42
     មាន
    0.41
    हरा
    0.41
     नामक
    0.41
     najbli
    0.41
    POSITIVE LOGITS
    monton
    0.43
    RING
    0.40
    INTERFACE
    0.37
     aven
    0.37
     Faktor
    0.37
    此之外
    0.36
     SUCH
    0.36
     RING
    0.35
    ྕ
    0.35
    شب
    0.34
    Activations Density 0.003%

    No Known Activations