© 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. 1310
    Prev
    Next
    INDEX
    Explanations

    introducing additional information

    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
    ’
    -3.03
     
    -2.98
     ”
    -2.66
    e
    -2.63
    к
    -2.47
    <b>
    -2.45
     unwavering
    -2.42
     sincere
    -2.36
    行く
    -2.31
     един
    -2.30
    POSITIVE LOGITS
    秶
    2.80
    ację
    2.73
    
    2.67
    ୌ
    2.66
    нутрен
    2.64
    ୬
    2.64
    They
    2.63
    It
    2.59
    diyah
    2.55
     Hacer
    2.53
    Activations Density 0.002%

    No Known Activations