© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84353
    Prev
    Next
    INDEX
    Explanations

    for fun or games

    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
     Cyr
    -0.82
    + 
    -0.82
     レンタル
    -0.81
    !</
    -0.79
     pomoc
    -0.75
     aprovechar
    -0.74
    χεία
    -0.73
    fir
    -0.73
    !
    -0.72
    Fig
    -0.71
    POSITIVE LOGITS
     kicks
    1.93
     giggles
    1.84
     laughs
    1.61
     fun
    1.58
     shits
    1.47
     lol
    1.34
     grins
    1.30
     LOL
    1.28
     chuckles
    1.24
     lul
    1.20
    Activations Density 0.022%

    No Known Activations