© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 73947
    Prev
    Next
    INDEX
    Explanations

    hyponatremia, adiponectin, Groupon, pontifier

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

    words containing "pon" like "hyponatremia", "adiponectin", "Groupon", and "Ponte".

    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
    0
    -3.06
    .”
    -2.75
    The
    -2.69
    та
    -2.66
    是很
    -2.64
    3
    -2.61
    也非常
    -2.55
    也很
    -2.36
     一个
    -2.34
    6
    -2.34
    POSITIVE LOGITS
    もお
    2.36
     hoger
    2.27
     archaic
    2.20
     owing
    2.14
     Muscles
    2.11
     religiously
    2.11
    ᛬
    2.11
     Якщо
    2.09
    pon
    2.08
     şir
    2.08
    Activations Density 0.015%

    No Known Activations