© 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. 34-GEMMASCOPE-RES-131K
    7. 78634
    Prev
    Next
    INDEX
    Explanations

    steel construction components

    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
     dirigida
    -0.89
    äldrar
    -0.88
    chés
    -0.82
     yöne
    -0.77
    elsa
    -0.77
    评论
    -0.77
    diği
    -0.76
    不仅仅
    -0.76
     экспер
    -0.75
     mää
    -0.75
    POSITIVE LOGITS
     rugged
    1.04
     steel
    1.02
     powder
    1.00
     construction
    1.00
    OPTIONAL
    0.97
     internal
    0.91
     optional
    0.87
     internally
    0.86
     door
    0.85
     heavy
    0.85
    Activations Density 0.033%

    No Known Activations