© 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. 1373
    Prev
    Next
    INDEX
    Explanations

    alternatives or provincial matters

    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
    grat
    1.27
    quir
    1.25
    amp
    1.18
    mac
    1.16
    ⅼ
    1.16
    etah
    1.15
    考試
    1.15
    exam
    1.13
    arch
    1.13
    apple
    1.12
    POSITIVE LOGITS
     cnpj
    1.53
     será
    1.47
     আগ্রহী
    1.39
    明日
    1.39
     tumhe
    1.35
    𝟘
    1.34
     fizemos
    1.33
     mendorong
    1.33
     queridos
    1.33
     tratta
    1.32
    Activations Density 0.242%

    No Known Activations