© 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. 696
    Prev
    Next
    INDEX
    Explanations

    web addresses

    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
    getConfiguration
    1.61
    𝐦
    1.51
    станов
    1.46
    Executed
    1.46
    𝐮
    1.42
    𝐱
    1.42
     Vien
    1.41
    𝑨
    1.39
    allen
    1.39
    боров
    1.39
    POSITIVE LOGITS
    gstatic
    1.91
    halter
    1.62
    ൂടെ
    1.52
    dish
    1.52
     maju
    1.44
    মাধ্য
    1.42
    이트
    1.42
     polyt
    1.41
     күзгү
    1.40
    langle
    1.40
    Activations Density 0.824%

    No Known Activations