© 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. 34533
    Prev
    Next
    INDEX
    Explanations

    Two plus, Two minus

    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
    ᾰ
    -0.84
    ciata
    -0.83
    ־ה
    -0.81
     Hef
    -0.81
    inien
    -0.80
     Sobald
    -0.79
    加工
    -0.78
    ുടെ
    -0.77
     comedian
    -0.77
     blueberry
    -0.77
    POSITIVE LOGITS
    zeiger
    0.77
     men
    0.76
     missing
    0.73
    IDO
    0.73
    Missing
    0.72
    Oak
    0.71
     Oak
    0.71
    solved
    0.69
     실패
    0.69
    ահ
    0.68
    Activations Density 0.011%

    No Known Activations