© 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. 190040
    Prev
    Next
    INDEX
    Explanations

    executive officer, interpreters, parent

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

    3 main characters

    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
    ísimo
    0.47
    璈
    0.46
    ísima
    0.46
     Centro
    0.46
    𝕘
    0.46
     usługi
    0.46
    ीडी
    0.45
    chrift
    0.45
    俦
    0.45
     प्रोसेसिंग
    0.44
    POSITIVE LOGITS
    advertising
    0.55
     وأ
    0.47
    ับ
    0.46
     analyzing
    0.43
     assisting
    0.43
    ovas
    0.43
    ؟
    0.43
     athletes
    0.43
     сказать
    0.43
    )\
    0.42
    Activations Density 0.000%

    No Known Activations