© 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. 48109
    Prev
    Next
    INDEX
    Explanations

    platform

    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
     because
    -2.14
     There
    -1.88
     Because
    -1.74
    1
    -1.67
     However
    -1.67
     Here
    -1.66
    because
    -1.66
    䴀
    -1.61
     Compared
    -1.61
     That
    -1.56
    POSITIVE LOGITS
    
    1.60
     BEING
    1.56
    螃
    1.54
    ROGEN
    1.51
     colonne
    1.43
     Hadoop
    1.43
     ayar
    1.41
     ſ
    1.40
     renk
    1.38
    ⏺
    1.38
    Activations Density 0.023%

    No Known Activations