© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 138991
    Prev
    Next
    INDEX
    Explanations

    the phrase 'pun intended'

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

    punny jokes

    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
    σ
    0.51
    常见的
    0.48
     ferrite
    0.47
    形状
    0.47
     Facial
    0.47
     Replica
    0.45
    Style
    0.44
     hologram
    0.44
     Toss
    0.44
    шее
    0.43
    POSITIVE LOGITS
     abuso
    0.59
     ideale
    0.53
    䡋
    0.47
     কৃত
    0.46
    ět
    0.46
     acto
    0.46
    ഗത
    0.45
     repas
    0.45
     manejo
    0.44
     conto
    0.44
    Activations Density 0.005%

    No Known Activations