© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 3342
    Prev
    Next
    INDEX
    Explanations

    dinam-ina, lism-ore, m-uff, M-oli

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

    words ending in -matic or -bile

    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_53_width_65k_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
    ा
    0.53
    ामध्ये
    0.50
    entwicklung
    0.50
    চ্ছন্ন
    0.49
    اا
    0.48
    าม
    0.44
    rops
    0.44
    로운
    0.44
    entwick
    0.44
    ﹰ
    0.43
    POSITIVE LOGITS
    atically
    1.12
    orphism
    1.09
    ageddon
    1.02
    obile
    1.00
    aterial
    0.99
    useum
    0.99
    orphic
    0.98
    ilitary
    0.98
    orphous
    0.97
    obiles
    0.96
    Activations Density 0.604%

    No Known Activations