© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 44063
    Prev
    Next
    INDEX
    Explanations

    light bulb jokes

    np_acts-logits-general · gemini-2.5-flash-lite

    phrasing and structure of “How many X does it take to change a light bulb?” jokes, especially the light-bulb question itself and its numeric setup.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
    职
    0.49
    ประจำ
    0.42
     تبدیلی
    0.42
     почвы
    0.41
     veer
    0.39
    では
    0.39
    뻣
    0.38
    现有
    0.38
    Nepal
    0.38
    ༣
    0.38
    POSITIVE LOGITS
     reiterated
    0.44
     Neutron
    0.41
     Jürgen
    0.40
     Arco
    0.40
    RICAL
    0.39
     ≤
    0.39
     blu
    0.39
     Cardano
    0.39
     AVE
    0.38
    \}.
    0.38
    Activations Density 0.003%

    No Known Activations