© 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. 80814
    Prev
    Next
    INDEX
    Explanations

    names, places, and programming terms

    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
    ㍑
    -2.80
    koszulka
    -2.66
    埸
    -2.61
     condicionado
    -2.58
    冏
    -2.55
     ランチ
    -2.53
    ſſen
    -2.50
     celebrates
    -2.47
    可以说
    -2.45
    sandalia
    -2.44
    POSITIVE LOGITS
    s
    3.08
    _
    3.02
    T
    2.72
    U
    2.70
    ]
    2.70
    vantaged
    2.67
    .
    2.66
    B
    2.58
    d
    2.56
     
    2.50
    Activations Density 0.004%

    No Known Activations