© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 16026
    Prev
    Next
    INDEX
    Explanations

    steps already taken

    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_13_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
    stArray
    1.65
    tune
    1.60
     MainWindow
    1.56
    sinya
    1.54
    ্ণ
    1.53
     gridSize
    1.52
    ㄴ
    1.52
    sts
    1.45
    髗
    1.44
    RowNum
    1.44
    POSITIVE LOGITS
     mitt
    1.43
    宣
    1.34
    ouml
    1.32
    uck
    1.32
    δή
    1.23
    offer
    1.22
    ન્યા
    1.17
    Avatar
    1.16
    engage
    1.15
    uso
    1.14
    Activations Density 0.000%

    No Known Activations