© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1918
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     curated
    1.74
     website
    1.59
     author
    1.52
    .)).
    1.51
    <start_of_image>
    1.48
     intriguing
    1.46
     additional
    1.46
     publisher
    1.44
     nifty
    1.42
    .
    1.42
    POSITIVE LOGITS
    Celula
    1.72
    λοι
    1.62
    Ḩ
    1.59
     meninos
    1.58
    zerel
    1.55
    [,]
    1.54
    Disciplina
    1.51
    䚰
    1.50
    ღვ
    1.48
    baixo
    1.46
    Activations Density 0.229%

    No Known Activations