© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 17492
    Prev
    Next
    INDEX
    Explanations

    cities and countries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    िला
    0.37
    ذا
    0.35
    ונ
    0.33
    гли
    0.33
     Restriction
    0.33
    者的
    0.32
    为其
    0.32
     내
    0.32
     Rede
    0.32
     correspondant
    0.32
    POSITIVE LOGITS
     США
    0.43
     Kyrgyzstan
    0.42
    zechoslovakia
    0.40
     سوریه
    0.39
     florida
    0.39
     England
    0.38
    ্ট
    0.38
     Florida
    0.37
     Connecticut
    0.37
     Франции
    0.37
    Activations Density 0.013%

    No Known Activations