© 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. 83771
    Prev
    Next
    INDEX
    Explanations

    listing items, proper nouns

    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
    ދ
    0.39
     diciembre
    0.38
    untary
    0.38
    eteen
    0.38
    elmi
    0.38
    orate
    0.37
     delinquency
    0.37
    hesized
    0.36
    ంచ
    0.36
    |,
    0.35
    POSITIVE LOGITS
    کو
    0.42
     convain
    0.40
     eng
    0.39
     ENG
    0.38
     सिया
    0.38
     والتي
    0.36
     які
    0.36
     Filament
    0.36
     হান
    0.36
     Kiểm
    0.35
    Activations Density 0.000%

    No Known Activations