© 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. 2076
    Prev
    Next
    INDEX
    Explanations

    录音, 熟练, 敌方, 促进, 味蕾

    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
     give
    0.79
     waveforms
    0.79
     insertion
    0.77
    ,
    0.76
     a
    0.76
     getting
    0.75
     What
    0.74
     It
    0.74
     it
    0.73
     folder
    0.73
    POSITIVE LOGITS
    力和
    0.99
    材
    0.97
    力
    0.97
    ادة
    0.89
    gameField
    0.87
     chế
    0.85
    生的
    0.85
    子的
    0.85
    عة
    0.85
     thức
    0.85
    Activations Density 0.094%

    No Known Activations