© 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. 201174
    Prev
    Next
    INDEX
    Explanations

    ambassadors and secretaries

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

    technical elements or parts

    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
     посте
    0.45
    ካል
    0.44
    มุม
    0.43
     أحد
    0.43
     احد
    0.42
    ၁
    0.42
    ów
    0.42
    ಗದ
    0.42
    дий
    0.41
    ใคร
    0.41
    POSITIVE LOGITS
     secretaries
    0.46
     Ambassadors
    0.45
     அமைச்ச
    0.44
     Secretaries
    0.43
    שה
    0.43
     ambassadors
    0.43
    ঞ্চলে
    0.43
    媽
    0.43
    ثل
    0.42
    ظم
    0.42
    Activations Density 0.001%

    No Known Activations