© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 39419
    Prev
    Next
    INDEX
    Explanations

    tty, ICS, Gilmore, EMR, Derry

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ‪.‬‬
    -2.83
    and
    -2.77
    皤
    -2.59
    狁
    -2.55
    饃
    -2.38
     juges
    -2.33
     kardashian
    -2.25
     fuq
    -2.25
    賅
    -2.23
    灕
    -2.19
    POSITIVE LOGITS
    </h3>
    2.58
    ↵↵
    2.33
     wichtigste
    2.23
    '
    2.23
     deği
    2.20
    ть
    2.16
    )
    2.13
     delapan
    2.08
     Cbd
    2.06
     Перейти
    2.05
    Activations Density 0.014%

    No Known Activations