© 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. 110842
    Prev
    Next
    INDEX
    Explanations

    attack submarine class

    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
    hubanes
    -0.79
    mbing
    -0.78
     destroyer
    -0.76
     destroy
    -0.75
    bibit
    -0.75
     periodicity
    -0.75
    pesa
    -0.73
    asier
    -0.72
    sao
    -0.72
    cuits
    -0.71
    POSITIVE LOGITS
     submarine
    2.38
     submarines
    2.38
     submer
    2.38
     Submarine
    1.88
     SUB
    1.78
     subs
    1.73
     Sub
    1.68
     суб
    1.66
    潜水
    1.64
     подвод
    1.59
    Activations Density 0.037%

    No Known Activations