© 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. 39103
    Prev
    Next
    INDEX
    Explanations

    theme parks and attractions

    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
    3
    -1.70
    ↵
    -1.64
    5
    -1.63
     n
    -1.60
    7
    -1.53
    9
    -1.52
    ha
    -1.52
     then
    -1.46
    4
    -1.45
     also
    -1.44
    POSITIVE LOGITS
    騖
    1.59
    ~:
    1.48
    orszá
    1.46
     kapture
    1.41
     抠
    1.40
    Gambas
    1.39
    nswer
    1.39
     monumento
    1.38
    tidumbre
    1.38
    Disney
    1.34
    Activations Density 0.013%

    No Known Activations