© 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. 73725
    Prev
    Next
    INDEX
    Explanations

    locations found in text

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

    proper nouns and locations

    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
     Macquarie
    0.42
    োপাধ্যায়
    0.41
    dol
    0.39
     Macmillan
    0.38
     esa
    0.38
    ()!=
    0.38
    ediaan
    0.37
     যুক্তরাষ্ট্রে
    0.37
    দিত
    0.37
     Hertfordshire
    0.36
    POSITIVE LOGITS
    They
    0.38
     radicals
    0.38
    कार्य
    0.38
    等地
    0.36
     गल
    0.36
    Were
    0.36
    Corn
    0.35
    焰
    0.35
    ுகிறார்கள்
    0.34
    Kind
    0.34
    Activations Density 0.001%

    No Known Activations