© 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. 10-GEMMASCOPE-RES-131K
    7. 84120
    Prev
    Next
    INDEX
    Explanations

    joking and kidding

    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_10/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
     ''
    -2.09
    ࿚
    -1.79
    เกง
    -1.70
    chenta
    -1.64
     ""
    -1.63
     bothers
    -1.61
    こんばん
    -1.61
    }}$.
    -1.59
    ˢ
    -1.58
     aesthetically
    -1.55
    POSITIVE LOGITS
    0
    2.02
     about
    2.02
    5
    1.98
    .
    1.80
     febbraio
    1.76
    各样的
    1.74
    wertig
    1.70
     $#
    1.68
    1
    1.68
    7
    1.66
    Activations Density 0.007%

    No Known Activations