© 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-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14691
    Prev
    Next
    INDEX
    Explanations

    VPN, SEO, innovation, allocation

    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
    𝒮
    3.03
     sConfig
    2.85
     জাহান
    2.75
    𝒟
    2.75
    âtel
    2.65
    ೋತಿ
    2.58
    ushchev
    2.56
     लकार
    2.55
    ဟုတ်
    2.51
     Firms
    2.45
    POSITIVE LOGITS
    lung
    2.39
    كور
    2.19
    Vine
    2.16
    ي
    1.98
    दार
    1.84
    챌
    1.83
    ভিং
    1.82
    jiv
    1.82
    ంగ్
    1.80
     پڑے
    1.80
    Activations Density 0.004%

    No Known Activations