© 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. 90757
    Prev
    Next
    INDEX
    Explanations

    Entity Framework or EF lenses

    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
     They
    -3.14
     ответил
    -2.84
    齁
    -2.56
     пришли
    -2.52
    꿉
    -2.50
    程度の
    -2.44
    i
    -2.42
    ться
    -2.41
     mesmos
    -2.39
    ギュア
    -2.34
    POSITIVE LOGITS
    </h3>
    2.55
    $
    2.34
    .
    2.33
    }
    2.25
     ascertain
    2.09
     semana
    2.05
    艿
    1.98
    {
    1.98
    ൎ
    1.95
    али
    1.94
    Activations Density 0.010%

    No Known Activations