© 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. 223842
    Prev
    Next
    INDEX
    Explanations

    foreign words and punctuation

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

    URLs in technical examples

    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
    Clinton
    0.40
    slots
    0.40
     క్
    0.40
     ಕಾಂಗ್ರೆ
    0.40
    Ing
    0.39
    ressions
    0.39
    𝐩
    0.38
     مرگ
    0.38
    сло
    0.38
    Shang
    0.38
    POSITIVE LOGITS
     solaire
    0.38
     Украине
    0.38
    ença
    0.38
    肝
    0.37
    प्रभात
    0.37
     Liver
    0.37
    )’
    0.36
     desech
    0.36
     liver
    0.36
     மனை
    0.36
    Activations Density 0.023%

    No Known Activations