© 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. 13876
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     clump
    0.60
     BOOL
    0.53
    bound
    0.52
    askets
    0.52
    簇
    0.52
    Bound
    0.52
    רט
    0.51
    incarn
    0.50
     crying
    0.49
     Yemen
    0.49
    POSITIVE LOGITS
     اکنون
    0.61
    ສາມາດ
    0.56
     elevar
    0.56
    犄
    0.55
    する場合
    0.55
     akci
    0.54
    osten
    0.54
    競爭
    0.53
    LookAndFeels
    0.53
     lleva
    0.53
    Activations Density 0.045%

    No Known Activations