© 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. 649
    Prev
    Next
    INDEX
    Explanations

    like magic, the core

    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
     ข้าง
    1.67
     各
    1.62
    rib
    1.60
     回転
    1.58
     teeth
    1.55
     này
    1.53
     disks
    1.53
    ровки
    1.52
     カード
    1.51
     shoes
    1.50
    POSITIVE LOGITS
    spender
    1.65
     unquestion
    1.55
    licz
    1.54
     মূলত
    1.52
    constant
    1.51
    holen
    1.50
    <unused340>
    1.42
    ⁵
    1.40
    comer
    1.40
    必然
    1.38
    Activations Density 2.886%

    No Known Activations