© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 123910
    Prev
    Next
    INDEX
    Explanations

    THC or UITable/Dyslexia

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

    acronyms and technical abbreviations like "THC", "UIT" and "lexia".

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ي
    -3.73
    ed
    -3.30
    i
    -3.05
    注意事
    -2.83
    ها
    -2.69
    as
    -2.59
     باسلام
    -2.50
    縢
    -2.48
    其妙
    -2.48
    acterísticas
    -2.48
    POSITIVE LOGITS
    E
    3.58
    F
    3.08
    ㉕
    3.06
    $
    3.00
    "
    2.83
    肫
    2.80
     ajouter
    2.58
    ations
    2.55
    N
    2.53
     uplifting
    2.52
    Activations Density 0.025%

    No Known Activations