© 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. 76547
    Prev
    Next
    INDEX
    Explanations

    copyright notices and code headers

    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
    ÊNCIA
    -0.75
     :");
    -0.69
    くださった
    -0.69
     Vaughan
    -0.68
    귀
    -0.66
    laug
    -0.66
     Besitzer
    -0.65
    lový
    -0.64
    推送
    -0.63
    titudine
    -0.63
    POSITIVE LOGITS
    zów
    0.72
    回合
    0.69
    จัด
    0.68
    utuhkan
    0.67
    scholars
    0.65
    バリ
    0.65
    isela
    0.65
    井
    0.64
     мира
    0.64
    onaut
    0.61
    Activations Density 0.061%

    No Known Activations