© 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. 12209
    Prev
    Next
    INDEX
    Explanations

    translucent and transparent

    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
    o
    -1.76
     Probably
    -1.56
    _
    -1.45
     gerais
    -1.34
     Therefore
    -1.34
     Surprisingly
    -1.34
     cryptic
    -1.31
     Also
    -1.30
    onuclear
    -1.30
     When
    -1.23
    POSITIVE LOGITS
     $\&$
    1.55
     micrófono
    1.53
     puissante
    1.50
    ݯ
    1.49
     первом
    1.48
    神
    1.48
    鑁
    1.45
    ⅅ
    1.43
    嘤
    1.42
    歃
    1.41
    Activations Density 0.062%

    No Known Activations