© 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. 13862
    Prev
    Next
    INDEX
    Explanations

    excel and spreadsheets

    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
    erste
    1.61
    e
    1.60
    থর
    1.54
     Bring
    1.47
    ه
    1.46
    ⃛
    1.45
    зив
    1.41
    亥
    1.39
    chter
    1.38
     Step
    1.37
    POSITIVE LOGITS
    oldCount
    2.26
     удо
    2.18
     סט
    2.10
    WebApi
    2.07
    лаб
    2.02
    ᴅ
    2.02
    ңү
    2.01
    យ
    2.00
     մե
    2.00
     רק
    1.99
    Activations Density 0.107%

    No Known Activations