© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 167920
    Prev
    Next
    INDEX
    Explanations

    foreign words and characters

    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
    液
    0.40
     quantifying
    0.38
     Somehow
    0.38
     sounding
    0.37
    bea
    0.36
    hyd
    0.35
    mining
    0.35
    hydration
    0.35
     mining
    0.35
     somehow
    0.35
    POSITIVE LOGITS
    裔
    0.41
    <^
    0.41
     tématu
    0.41
     Komponenten
    0.40
    żs
    0.40
     मृतकों
    0.39
     तम्
    0.39
    各大
    0.39
     儿童
    0.39
     kotlinx
    0.38
    Activations Density 0.001%

    No Known Activations