© 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. 69942
    Prev
    Next
    INDEX
    Explanations

    professions and roles

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

    depending on

    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
    त्रे
    0.46
    你自己
    0.46
    ستوى
    0.45
     můžete
    0.44
    僄
    0.44
    امد
    0.43
    estyle
    0.43
     disconnecting
    0.43
    ુભ
    0.42
    köy
    0.42
    POSITIVE LOGITS
     대부분
    0.48
    გ
    0.46
    tt
    0.46
     მი
    0.46
     interferon
    0.45
    xv
    0.45
    times
    0.45
    底层
    0.43
     हान
    0.43
     पालक
    0.43
    Activations Density 0.001%

    No Known Activations