© 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. 190859
    Prev
    Next
    INDEX
    Explanations

    limits artistic expression

    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
    hentication
    0.37
    ⴻ
    0.37
     vertu
    0.36
     JOURNAL
    0.36
    pite
    0.36
    ctus
    0.35
     جيد
    0.35
    arsanız
    0.35
     кеңселер
    0.35
    🧭
    0.35
    POSITIVE LOGITS
    Cor
    0.40
    Dis
    0.38
    Drop
    0.38
    drop
    0.38
    Complement
    0.37
    Module
    0.37
    Quiz
    0.37
     Dub
    0.37
     drop
    0.36
     Repair
    0.36
    Activations Density 0.000%

    No Known Activations