© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2513
    Prev
    Next
    INDEX
    Explanations

    combine, toss, add, stir

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_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
     бума
    0.69
    鐵
    0.68
    tection
    0.68
     मामा
    0.67
    iglia
    0.66
    etting
    0.65
     ቁ
    0.65
     숫
    0.65
     ശ്രീ
    0.65
     भैया
    0.64
    POSITIVE LOGITS
     season
    0.81
     Beat
    0.75
    æn
    0.74
     Season
    0.73
     Toss
    0.72
    reserve
    0.72
    Beat
    0.71
     Sal
    0.71
    rea
    0.69
     toss
    0.68
    Activations Density 0.054%

    No Known Activations