© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199905
    Prev
    Next
    INDEX
    Explanations

    our

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

    jokes and their basis

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     John
    0.46
     Jacob
    0.46
     جزء
    0.46
     Residential
    0.44
    Z
    0.44
     Lie
    0.43
     BAM
    0.43
     Gall
    0.43
    John
    0.42
     Part
    0.42
    POSITIVE LOGITS
     जिसने
    0.49
    irmek
    0.47
     በጣም
    0.46
     crédito
    0.46
    뤼
    0.46
    購物
    0.45
    クス
    0.44
     modernize
    0.44
     море
    0.44
    OTH
    0.43
    Activations Density 0.000%

    No Known Activations