© 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. 57174
    Prev
    Next
    INDEX
    Explanations

    ox prefix

    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
     sofia
    -0.87
     semarang
    -0.83
    それでも
    -0.80
     canapé
    -0.79
    それにしても
    -0.75
     Michoacán
    -0.74
    phia
    -0.72
     surabaya
    -0.71
     Farewell
    -0.71
    相對
    -0.71
    POSITIVE LOGITS
     Ox
    1.48
     ox
    1.34
    Ox
    1.32
     OX
    1.23
     Oxy
    1.02
    Oxy
    0.88
     aventura
    0.88
    Oxford
    0.88
     Cambridge
    0.87
    Animating
    0.87
    Activations Density 0.022%

    No Known Activations