© 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. 70720
    Prev
    Next
    INDEX
    Explanations

    "i wish i had"

    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
     baterie
    -1.84
    紲
    -1.78
    誣
    -1.71
     zboží
    -1.67
     Erwartungen
    -1.61
     masina
    -1.61
     manuelle
    -1.59
    zwei
    -1.59
     engraçadas
    -1.59
    祤
    -1.58
    POSITIVE LOGITS
     which
    1.68
    ↵
    1.64
     lacks
    1.59
     Nome
    1.52
    "
    1.41
     of
    1.40
    Eyed
    1.40
    /
    1.38
    [
    1.34
     rises
    1.33
    Activations Density 0.004%

    No Known Activations