© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 109681
    Prev
    Next
    INDEX
    Explanations

    testing and acceptance criteria

    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
    happily
    -0.78
    芸
    -0.77
    customized
    -0.76
     franch
    -0.76
    udal
    -0.75
     Temporal
    -0.74
     Eth
    -0.73
    醣
    -0.72
    Hazardous
    -0.72
    举办
    -0.70
    POSITIVE LOGITS
     testing
    1.11
     sampling
    1.09
     test
    1.07
     acceptance
    1.01
     samples
    0.98
     tests
    0.97
    sampling
    0.91
    test
    0.89
    Lot
    0.88
    Sampling
    0.86
    Activations Density 0.003%

    No Known Activations