© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 354
    Prev
    Next
    INDEX
    Explanations

    hydrological and simulation modeling

    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
    kosť
    -0.71
     recursively
    -0.71
     humorous
    -0.70
    stdafx
    -0.70
     kneeling
    -0.68
    osum
    -0.67
     Langford
    -0.67
    ஜ
    -0.66
     MediaQuery
    -0.66
    őre
    -0.65
    POSITIVE LOGITS
    model
    0.90
     solver
    0.88
     celer
    0.85
     HEC
    0.84
     modeling
    0.84
     model
    0.84
    getModel
    0.82
     TIN
    0.81
     Vege
    0.79
    ツイン
    0.79
    Activations Density 0.010%

    No Known Activations