© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 85915
    Prev
    Next
    INDEX
    Explanations

    other followed by symbols or word parts

    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
    儅
    -1.92
     позволяет
    -1.68
    начала
    -1.64
     PUSTAKA
    -1.58
     Herausgeber
    -1.58
    }=\
    -1.57
     and
    -1.55
     erste
    -1.54
     poderosa
    -1.53
    ULTURAL
    -1.52
    POSITIVE LOGITS
    The
    3.05
    瀦
    2.45
    了一会儿
    2.28
    媖
    2.23
    ༑
    2.19
    
    2.17
    
    2.14
    塤
    2.13
     anderes
    2.09
    ésil
    2.09
    Activations Density 0.007%

    No Known Activations