© 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. 93564
    Prev
    Next
    INDEX
    Explanations

    clothing, menswear

    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
    dings
    -0.93
     acompañar
    -0.84
     keç
    -0.84
     maaaring
    -0.84
    giver
    -0.81
     RESTAUR
    -0.81
     WAYNE
    -0.80
     PHILL
    -0.80
     pohy
    -0.80
    although
    -0.80
    POSITIVE LOGITS
     Casual
    0.98
     casual
    0.85
    Casual
    0.83
    Sergio
    0.82
     Il
    0.80
    Uber
    0.80
     menswear
    0.79
     Thursday
    0.78
    чному
    0.77
     周
    0.75
    Activations Density 0.001%

    No Known Activations