© 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. 42158
    Prev
    Next
    INDEX
    Explanations

    medial or demi

    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
    <i>
    -2.70
    餮
    -2.53
     ''
    -2.34
     desarrollando
    -2.25
    ਃ
    -2.16
     gjerne
    -2.09
     ‘‘
    -2.06
     owing
    -2.05
     respectivas
    -1.99
    M
    -1.99
    POSITIVE LOGITS
    lossians
    2.52
     habitudes
    2.23
     стоковые
    2.22
     現貨
    2.20
    ться
    2.17
    沺
    2.17
    
    2.16
     métallique
    2.13
    neling
    2.09
     techo
    2.08
    Activations Density 0.003%

    No Known Activations