© 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. 83633
    Prev
    Next
    INDEX
    Explanations

    puns or wordplay

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    OGRAPHIC
    0.47
    বরা
    0.45
    gian
    0.43
     BOTTOM
    0.43
    巻き
    0.43
     TRANSACTION
    0.43
    lbrack
    0.43
    苅
    0.42
    ρε
    0.41
    爐
    0.41
    POSITIVE LOGITS
    威尔
    0.46
     garant
    0.45
     z
    0.44
     drop
    0.43
     luft
    0.43
     prophet
    0.43
     extr
    0.42
     guarantee
    0.42
     विकल्प
    0.42
     sullen
    0.42
    Activations Density 0.009%

    No Known Activations