© 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. 222483
    Prev
    Next
    INDEX
    Explanations

    underground detonations

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

    Kai has, research ., echoes ’, simulated rules

    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
     ő
    0.53
     ហើយ
    0.52
     ಇದ್ದ
    0.50
    seiten
    0.50
     äußer
    0.49
     Einen
    0.49
    ikation
    0.48
     ንጥረ
    0.48
    grö
    0.48
    zni
    0.47
    POSITIVE LOGITS
    اق
    0.46
    ﺭ
    0.44
    的确
    0.43
    CurrentByte
    0.43
    িত্ব
    0.43
    fraction
    0.43
    ปัจจุบัน
    0.43
    ﻡ
    0.43
    เปอร์
    0.42
    오늘은
    0.42
    Activations Density 0.000%

    No Known Activations