© 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-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 13831
    Prev
    Next
    INDEX
    Explanations

    programming languages and SSH

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     dorsal
    1.77
     Vật
    1.62
    嬤
    1.62
    館
    1.61
    េច
    1.61
     PMID
    1.59
     jail
    1.55
     eukaryotic
    1.55
    葦
    1.55
     Jail
    1.53
    POSITIVE LOGITS
    Bloomberg
    1.54
     consultancy
    1.33
     Bloomberg
    1.32
    证券
    1.32
    投資
    1.31
     immobilier
    1.27
     investment
    1.26
     bullion
    1.23
    Investors
    1.21
     اوس
    1.19
    Activations Density 0.416%

    No Known Activations