© 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. 18698
    Prev
    Next
    INDEX
    Explanations

    team or product names

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

    Geography and types

    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
    리아
    0.23
     resurrection
    0.21
    辭
    0.21
     maç
    0.21
     setSelected
    0.21
     zwycię
    0.21
    리가
    0.21
    霊
    0.20
     Yên
    0.20
     recordó
    0.20
    POSITIVE LOGITS
    अमेर
    0.25
    ड्रो
    0.24
    produkt
    0.24
     Velcro
    0.24
    folge
    0.23
    imes
    0.23
     বিষয়টি
    0.23
     प्रोसे
    0.23
    öny
    0.22
     welt
    0.22
    Activations Density 0.057%

    No Known Activations