© 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. 119545
    Prev
    Next
    INDEX
    Explanations

    shopping cart

    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
    㩒
    -1.45
    蹓
    -1.42
    这里
    -1.42
    2
    -1.41
    6
    -1.38
     vokal
    -1.36
     /**
    -1.35
    釕
    -1.34
    ется
    -1.34
    sc
    -1.33
    POSITIVE LOGITS
    <bos>
    1.66
     containing
    1.47
     Профиль
    1.41
     silêncio
    1.37
    ністю
    1.35
     resalt
    1.34
    ৢ
    1.34
     compromiso
    1.34
    MAXN
    1.33
    髣
    1.31
    Activations Density 0.006%

    No Known Activations