© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91710
    Prev
    Next
    INDEX
    Explanations

    paved surfaces

    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
    <mask>
    -0.82
    ushman
    -0.80
     propriétés
    -0.75
     efectivos
    -0.73
    니다
    -0.73
    騨
    -0.71
    尷
    -0.71
    tieri
    -0.71
     ámbitos
    -0.71
    Cols
    -0.70
    POSITIVE LOGITS
     paved
    2.53
     paving
    2.45
     pavement
    2.42
     pavements
    1.97
     asphalt
    1.92
     pave
    1.82
     Paving
    1.76
     Pavement
    1.64
     concrete
    1.63
     tarmac
    1.44
    Activations Density 0.018%

    No Known Activations