© 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. 22-GEMMASCOPE-RES-131K
    7. 13622
    Prev
    Next
    INDEX
    Explanations

    statistics, metrics, counting

    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_22/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
     öf
    -1.08
    ầm
    -1.08
    Tracce
    -0.99
    requirements
    -0.93
    熊猫
    -0.92
     uden
    -0.86
    口碑
    -0.84
    abyte
    -0.83
    ולוג
    -0.83
     obnoxious
    -0.82
    POSITIVE LOGITS
     statistics
    2.13
     statistical
    2.00
     statistic
    1.66
     stats
    1.57
    统计
    1.52
     Statistics
    1.48
     Statistical
    1.44
     statistically
    1.39
     statysty
    1.38
     metrics
    1.35
    Activations Density 0.180%

    No Known Activations