© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4847
    Prev
    Next
    INDEX
    Explanations

    explaining joke punchlines

    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_13_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
     وأ
    1.55
     في
    1.48
     ومن
    1.45
     în
    1.42
     يت
    1.37
     وت
    1.36
     ي
    1.35
     تت
    1.33
     وم
    1.30
     në
    1.28
    POSITIVE LOGITS
     guess
    0.81
    isman
    0.79
     credit
    0.76
    போதும்
    0.76
     general
    0.75
     discour
    0.75
     humorous
    0.74
     commend
    0.74
    decorator
    0.74
     talented
    0.73
    Activations Density 0.002%

    No Known Activations