Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 8421
    Prev
    Next
    INDEX
    Explanations

    risk management and exposure

    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
    ΡΑ
    -0.81
     religieuse
    -0.78
     scap
    -0.77
     вспо
    -0.76
    mények
    -0.75
    APPING
    -0.75
    熵
    -0.75
     Dordrecht
    -0.75
    !」
    -0.74
     мя
    -0.74
    POSITIVE LOGITS
     concentration
    1.12
     Concentration
    1.11
    Concentration
    1.05
     exposure
    1.03
    concentration
    1.02
     political
    1.00
     Exposure
    0.99
    execution
    0.93
    exposure
    0.92
     Political
    0.90
    Activations Density 0.011%

    No Known Activations