© 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. 70216
    Prev
    Next
    INDEX
    Explanations

    reckless indulgence and debauchery

    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
     pensive
    -0.79
     greifen
    -0.75
     shivering
    -0.75
    िट
    -0.73
     ingresso
    -0.73
    ppchen
    -0.72
     mutilated
    -0.72
    pdo
    -0.71
    elos
    -0.70
     ricerche
    -0.70
    POSITIVE LOGITS
     hedon
    1.88
     reckless
    1.87
     wild
    1.81
     partying
    1.81
     libert
    1.70
     carefree
    1.70
     irresponsible
    1.53
     lifestyle
    1.49
    libert
    1.47
     promiscu
    1.46
    Activations Density 0.059%

    No Known Activations