© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106820
    Prev
    Next
    INDEX
    Explanations

    puns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Prest
    -0.83
    ိ
    -0.83
    czyn
    -0.76
     devono
    -0.75
     ngược
    -0.75
    ḵ
    -0.74
     хло
    -0.72
     dikt
    -0.71
    Примеча
    -0.70
    bben
    -0.70
    POSITIVE LOGITS
     pun
    4.25
     puns
    3.38
    pun
    2.91
     Pun
    2.63
    Pun
    2.48
    PUN
    2.34
     PUN
    2.33
     play
    1.89
     groan
    1.64
    play
    1.59
    Activations Density 0.026%

    No Known Activations