© 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. 21824
    Prev
    Next
    INDEX
    Explanations

    major sporting events

    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
    激烈
    -1.61
    “
    -1.61
     или
    -1.60
    veloppement
    -1.60
     qualquer
    -1.59
     dieser
    -1.50
     یا
    -1.50
     atau
    -1.50
    ்க
    -1.47
    थि
    -1.45
    POSITIVE LOGITS
     minute
    1.58
    魠
    1.47
    全然
    1.42
    🫓
    1.41
     everybody
    1.41
     divertido
    1.34
     costuma
    1.34
     gagné
    1.32
    ässe
    1.32
     tuta
    1.30
    Activations Density 0.069%

    No Known Activations