© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57922
    Prev
    Next
    INDEX
    Explanations

    Armstrong, Louis, Systems, Linux, Army

    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
    adda
    -0.84
     cư
    -0.81
    graf
    -0.78
     наз
    -0.77
    тивной
    -0.74
    ఢ
    -0.74
    hape
    -0.74
    =[
    -0.74
    ῥ
    -0.74
     taj
    -0.73
    POSITIVE LOGITS
    하지
    0.86
    壟
    0.84
     rekomendasi
    0.75
    apartament
    0.73
     guan
    0.71
     Armstrong
    0.71
    除了
    0.70
    ？？
    0.70
     pembaca
    0.70
    tembro
    0.69
    Activations Density 0.030%

    No Known Activations