© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117034
    Prev
    Next
    INDEX
    Explanations

    EO or O followed by certain words

    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
    ждены
    -0.74
    peso
    -0.71
    phology
    -0.70
    ALLAS
    -0.69
    ophe
    -0.68
    phism
    -0.68
    oshiba
    -0.68
    usable
    -0.67
     Ponce
    -0.67
    mə
    -0.67
    POSITIVE LOGITS
     göm
    0.81
    玟
    0.74
     depar
    0.73
     مختلف
    0.72
     coreano
    0.72
    ਂ
    0.71
    jin
    0.71
    itosan
    0.71
    ео
    0.69
     migrant
    0.69
    Activations Density 0.025%

    No Known Activations