© 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. 6720
    Prev
    Next
    INDEX
    Explanations

    International conferences and organizations

    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
     condições
    -0.89
    ystick
    -0.85
    tisp
    -0.85
     jurisdiction
    -0.83
    faro
    -0.79
    perto
    -0.79
     žád
    -0.79
     procedere
    -0.78
    別人
    -0.77
    行きたい
    -0.77
    POSITIVE LOGITS
     International
    1.14
    国际
    1.11
     international
    1.09
    International
    1.06
    ETHOD
    1.05
     internationale
    0.96
     garda
    0.93
    ({
    
    0.91
     Workshop
    0.91
     långt
    0.90
    Activations Density 0.008%

    No Known Activations