© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 107288
    Prev
    Next
    INDEX
    Explanations

    demographic and social characteristics

    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
     Trauma
    -0.87
     спокойно
    -0.82
     localize
    -0.80
     <<<
    -0.79
    Trauma
    -0.79
    grading
    -0.78
     sade
    -0.77
     gastronomía
    -0.77
     DAN
    -0.76
    ɑ
    -0.75
    POSITIVE LOGITS
     transitions
    1.10
     patterns
    1.06
    Transitions
    1.02
     transition
    0.95
     arrangements
    0.95
     timing
    0.94
    hány
    0.94
     households
    0.93
     üst
    0.93
     cores
    0.92
    Activations Density 0.164%

    No Known Activations