© 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. 40-GEMMASCOPE-2-RES-262K
    7. 211936
    Prev
    Next
    INDEX
    Explanations

    non-english 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_40_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
    _:
    0.39
     cięż
    0.38
     bagian
    0.38
    quinox
    0.37
     brought
    0.37
     compared
    0.37
    :]:
    0.37
     separated
    0.37
     accompagne
    0.36
     commented
    0.36
    POSITIVE LOGITS
     dominante
    0.40
    ាវ
    0.39
    بار
    0.38
    ټر
    0.38
    ্ব
    0.37
    يار
    0.37
     गहरे
    0.36
    風
    0.36
     خو
    0.36
    巧妙
    0.36
    Activations Density 0.002%

    No Known Activations