© 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. 9977
    Prev
    Next
    INDEX
    Explanations

    Redis usage and integration

    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
     头像
    -2.42
     Why
    -2.41
     ursprünglich
    -2.31
    2
    -2.28
    ))
    -2.23
     Kennt
    -2.20
     എ
    -2.20
     AdapterView
    -2.20
     realización
    -2.17
     originally
    -2.16
    POSITIVE LOGITS
    there
    3.47
    нет
    2.55
    they
    2.55
    ㆆ
    2.53
     ''
    2.41
     peruano
    2.33
    tować
    2.30
    鏨
    2.28
    after
    2.27
     eléctrico
    2.25
    Activations Density 0.002%

    No Known Activations