© 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. 10080
    Prev
    Next
    INDEX
    Explanations

    with an object in hand

    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
     there
    -2.34
     '
    -1.63
     it
    -1.61
    ↵
    -1.59
    .'
    -1.57
    ăzi
    -1.53
    '
    -1.52
     has
    -1.48
    ↵↵
    -1.46
     people
    -1.41
    POSITIVE LOGITS
     Kenntnis
    1.67
    𖣘
    1.58
     respective
    1.58
     informaci
    1.56
    ჻
    1.55
    素敵な
    1.52
    nitř
    1.52
    ⌑
    1.48
    と思い
    1.47
    𓆝
    1.44
    Activations Density 0.022%

    No Known Activations