© 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. 229032
    Prev
    Next
    INDEX
    Explanations

    3rd noun, location noun

    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
    ও
    0.50
    ﺪ
    0.45
     narrowing
    0.45
     ಮಿ
    0.45
     খ
    0.43
     ಉ
    0.42
    live
    0.42
    :"",
    0.42
    ồm
    0.42
    ventana
    0.42
    POSITIVE LOGITS
     वाढत
    0.47
    вича
    0.45
    никам
    0.45
     enjoys
    0.45
    нера
    0.45
    🏌
    0.45
     derivadas
    0.43
     مکمل
    0.43
     เรียก
    0.43
     पर्यंत
    0.43
    Activations Density 0.000%

    No Known Activations