© 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. 105621
    Prev
    Next
    INDEX
    Explanations

    URLs ending in path segments

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

    URL path separators, particularly the forward slash in web addresses and file paths.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
    {
    -1.92
    ]
    -1.52
    密的
    -1.45
    жья
    -1.45
    '
    -1.42
    agles
    -1.38
     частности
    -1.38
    凝土
    -1.37
    ໊
    -1.35
    </h3>
    -1.34
    POSITIVE LOGITS
    Zdroje
    1.40
     restoran
    1.37
    呖
    1.33
    ４
    1.32
     of
    1.32
    CastException
    1.26
    Размеры
    1.26
    ırken
    1.26
     operacional
    1.26
     ساعد
    1.24
    Activations Density 0.012%

    No Known Activations