© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60864
    Prev
    Next
    INDEX
    Explanations

    divine or extraordinary figures

    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
    maßen
    -1.45
    hörige
    -1.43
    𝓡
    -1.42
    浤
    -1.42
    EVER
    -1.42
     gyors
    -1.41
    cribing
    -1.38
    齜
    -1.38
     Мария
    -1.38
    れたら
    -1.38
    POSITIVE LOGITS
     help
    1.77
     want
    1.67
     use
    1.50
    ]
    1.46
     name
    1.45
     there
    1.40
     time
    1.40
     would
    1.30
     появление
    1.30
     ulter
    1.29
    Activations Density 0.049%

    No Known Activations