© 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. 98548
    Prev
    Next
    INDEX
    Explanations

    numbers like 100

    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
    嚳
    -1.98
    に行って
    -1.92
    corrhi
    -1.88
     ส์
    -1.84
    ())
    -1.69
     Arbeitnehmer
    -1.69
    mohon
    -1.68
     noches
    -1.64
    ممنون
    -1.63
     beroperasi
    -1.61
    POSITIVE LOGITS
    they
    1.77
    ↵
    1.75
    ⽼
    1.56
    🔹
    1.54
     geometr
    1.52
    尽快
    1.48
    ensões
    1.45
    or
    1.45
    ability
    1.41
    끫
    1.39
    Activations Density 0.024%

    No Known Activations