© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 83708
    Prev
    Next
    INDEX
    Explanations

    wood types and materials

    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
     igu
    -0.91
     poppies
    -0.86
     snails
    -0.83
    縈
    -0.82
     ferns
    -0.78
    能让
    -0.75
    ੱਚ
    -0.73
     الساعة
    -0.73
    簡易
    -0.73
     zpra
    -0.73
    POSITIVE LOGITS
     oak
    1.34
     hardwood
    1.23
     hardwoods
    1.13
     species
    1.08
     Oak
    1.07
     pine
    1.02
     Pine
    1.02
     African
    0.98
     Brazilian
    0.97
     Ash
    0.94
    Activations Density 0.021%

    No Known Activations