© 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. 34-GEMMASCOPE-RES-131K
    7. 59121
    Prev
    Next
    INDEX
    Explanations

    item, product, material descriptions

    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_34/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
     puso
    -0.80
    Pek
    -0.77
     გ
    -0.71
    BOYS
    -0.70
    种类
    -0.69
    glied
    -0.68
    washingtonpost
    -0.68
     HERE
    -0.68
     пое
    -0.67
    ofi
    -0.67
    POSITIVE LOGITS
     article
    1.19
     materials
    1.18
     descriptions
    1.17
     item
    1.13
     material
    1.12
     articles
    1.09
     articolo
    1.04
     specifications
    1.02
     inventory
    0.99
     description
    0.98
    Activations Density 0.011%

    No Known Activations