© 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. 54004
    Prev
    Next
    INDEX
    Explanations

    scientific testing and experiments

    np_acts-logits-general · gemini-2.5-flash-lite

    scientific research methodologies and experimental procedures in technical studies.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     Calculations
    -0.94
    קות
    -0.83
     расс
    -0.77
     estadio
    -0.75
    getApplication
    -0.74
     masculinos
    -0.74
     wipes
    -0.72
    сько
    -0.71
     Excavation
    -0.71
    tacte
    -0.69
    POSITIVE LOGITS
     tests
    2.39
     test
    2.28
     testing
    2.13
     experiments
    1.87
     Tests
    1.64
     experimental
    1.63
     laboratory
    1.59
     experiment
    1.54
     experimentation
    1.53
    tests
    1.52
    Activations Density 0.045%

    No Known Activations