© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 124668
    Prev
    Next
    INDEX
    Explanations

    next and subsequent events/items

    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
    鬟
    -1.72
    过去了
    -1.45
    olybden
    -1.38
     วัน
    -1.38
    crites
    -1.37
    Gruppo
    -1.36
    罡
    -1.35
    ڧ
    -1.35
    ないです
    -1.35
     cambiando
    -1.35
    POSITIVE LOGITS
    ",
    2.05
    li
    1.59
    se
    1.56
    
    1.54
    ra
    1.53
    ner
    1.52
    ate
    1.49
    </h2>
    1.47
    ',
    1.44
    AMILTON
    1.43
    Activations Density 0.007%

    No Known Activations