© 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. 15251
    Prev
    Next
    INDEX
    Explanations

    att followed by error or suffix

    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
    TING
    0.68
     toes
    0.60
     exclusion
    0.57
    TINGS
    0.56
    udiant
    0.56
    剁
    0.56
     excision
    0.55
    滓
    0.55
    ர
    0.54
    そんな
    0.54
    POSITIVE LOGITS
     Att
    1.00
    Att
    0.94
     att
    0.89
    att
    0.87
    Attk
    0.75
    ılan
    0.74
    ATT
    0.68
    ат
    0.66
     reasonable
    0.66
     আত
    0.65
    Activations Density 0.142%

    No Known Activations