© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14049
    Prev
    Next
    INDEX
    Explanations

    nuclear followed by noun

    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_10/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
    .”
    -2.00
     íntegra
    -1.67
    
    -1.63
     theses
    -1.59
    This
    -1.59
    '
    -1.59
    ".$
    -1.56
    全是
    -1.51
    ߕ
    -1.46
    。“
    -1.45
    POSITIVE LOGITS
    ↵
    1.81
    nuclear
    1.70
    Nuclear
    1.64
    紲
    1.51
     folgenden
    1.50
     analiza
    1.48
     doctrina
    1.43
     flota
    1.41
    zelfde
    1.41
     preocupa
    1.41
    Activations Density 0.018%

    No Known Activations