© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 151759
    Prev
    Next
    INDEX
    Explanations

    military terms and operations

    np_acts-logits-general · gemini-2.5-flash-lite

    delivery services

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    apot
    0.49
     incumbent
    0.48
    ab
    0.47
    ben
    0.46
    bil
    0.46
    abel
    0.45
    owany
    0.44
    덕
    0.44
    ді
    0.44
    assi
    0.44
    POSITIVE LOGITS
    .~(\
    0.50
     médias
    0.48
     realizadas
    0.47
     ভূমিকম্প
    0.46
    ங்களில்
    0.46
     tens
    0.46
     بعد
    0.45
     मित्र
    0.45
    居住
    0.45
     개최
    0.45
    Activations Density 0.001%

    No Known Activations