© 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
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 70973
    Prev
    Next
    INDEX
    Explanations

    programming or foreign words

    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
    な
    0.48
     deme
    0.43
    РЕ
    0.42
    ผ
    0.41
     homegrown
    0.41
    ве
    0.40
    ات
    0.39
    ながら
    0.39
     podczas
    0.39
    תי
    0.39
    POSITIVE LOGITS
    🍒
    0.49
    thisobject
    0.45
     Payroll
    0.45
    ával
    0.43
    lepší
    0.43
     перехода
    0.43
     Happen
    0.43
     Estimated
    0.42
    mıştır
    0.42
    🚄
    0.42
    Activations Density 0.001%

    No Known Activations