© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 143710
    Prev
    Next
    INDEX
    Explanations

    Europe

    np_acts-logits-general · gemini-2.5-flash-lite

    evaluating learning concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     प्रीम
    0.51
     adesso
    0.48
    ็ว
    0.48
    ṕ
    0.47
    犾
    0.47
    cję
    0.47
     प्रोसे
    0.46
    reto
    0.46
    妠
    0.46
    𝓷
    0.45
    POSITIVE LOGITS
     Luton
    0.50
     Hindi
    0.46
     पैदल
    0.46
     Euros
    0.45
     Trapez
    0.44
     Deutschland
    0.44
     Box
    0.42
     separable
    0.42
     Europe
    0.42
     Gober
    0.42
    Activations Density 0.000%

    No Known Activations