© 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. 45692
    Prev
    Next
    INDEX
    Explanations

    setting colors in code

    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
    侍
    -0.82
    toFixed
    -0.78
    }$​
    -0.77
     дисци
    -0.75
    丞
    -0.73
     #
    -0.71
     muslin
    -0.69
     округ
    -0.69
    чам
    -0.68
    gesterone
    -0.68
    POSITIVE LOGITS
    definecolor
    0.92
    siren
    0.90
    timberland
    0.87
     WHITE
    0.84
     kola
    0.83
    UIColor
    0.82
     mixture
    0.79
    προ
    0.79
    premiere
    0.79
     conſ
    0.79
    Activations Density 0.018%

    No Known Activations