© 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. 33422
    Prev
    Next
    INDEX
    Explanations

    Chapter President, Guild Member, Board Director

    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
    leadership
    -0.84
    考虑
    -0.76
    考慮
    -0.75
    çs
    -0.75
    kmale
    -0.75
     fasse
    -0.75
    ลอง
    -0.75
    artigen
    -0.75
    ENED
    -0.74
    Création
    -0.73
    POSITIVE LOGITS
     publicity
    1.27
     Publicity
    1.09
     Education
    1.07
     education
    1.01
     Overall
    1.00
     immediate
    0.97
     educational
    0.95
     co
    0.95
     communications
    0.94
     Website
    0.93
    Activations Density 0.015%

    No Known Activations