© 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. 157245
    Prev
    Next
    INDEX
    Explanations

    multilingualism greetings

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

    complicated descriptive terms

    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
    Ampl
    0.48
     الاستفهام
    0.47
     subito
    0.46
    UNION
    0.45
     Acquisitions
    0.45
    Yi
    0.44
    鏉
    0.43
    Oui
    0.43
    Qu
    0.43
    Collector
    0.42
    POSITIVE LOGITS
     infección
    0.54
     человек
    0.48
    ciencia
    0.48
     गुरुग्राम
    0.47
    だよ
    0.46
     გ
    0.45
     वनस्पती
    0.45
     നമഃ
    0.45
     ocurrió
    0.45
     நோய்
    0.45
    Activations Density 0.002%

    No Known Activations