© 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-3-12B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 6464
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_31_width_16k_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
    ينات
    0.70
     sebelumnya
    0.69
     انها
    0.68
     घी
    0.63
    c
    0.63
     لس
    0.63
    previously
    0.62
     sensi
    0.62
    g
    0.62
    ب
    0.62
    POSITIVE LOGITS
     uitge
    0.82
    пону
    0.74
    GameObject
    0.74
     interoper
    0.72
    🄴
    0.72
    ΡΑ
    0.71
     políticas
    0.68
    UR
    0.67
    এন
    0.66
    ská
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.