© 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. 53984
    Prev
    Next
    INDEX
    Explanations

    numbers followed by words or names

    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
     Nab
    -0.69
     Weimar
    -0.69
    不然
    -0.68
    scissors
    -0.67
     mesures
    -0.67
     motorcycles
    -0.66
     dilated
    -0.66
     Januar
    -0.65
    читы
    -0.65
     Marburg
    -0.65
    POSITIVE LOGITS
     edema
    0.84
     Heartland
    0.82
     womit
    0.77
     Feeder
    0.76
    chow
    0.76
    イク
    0.75
    🐥
    0.74
    甲
    0.74
     ظهر
    0.73
    ٩
    0.73
    Activations Density 0.010%

    No Known Activations