© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2571
    Prev
    Next
    INDEX
    Explanations

    unique identifiers

    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
    olition
    2.71
     сло
    2.71
    弛
    2.56
     gathering
    2.54
    થમ
    2.36
     booth
    2.36
    度
    2.35
    縷
    2.32
    ugs
    2.25
    XA
    2.25
    POSITIVE LOGITS
    GOT
    2.67
    xcodeproj
    2.53
    ா
    2.49
    classpath
    2.46
    ಘ
    2.40
     Displaystyle
    2.35
    kové
    2.33
    ில்
    2.29
    みに
    2.29
    िप्स
    2.27
    Activations Density 0.303%

    No Known Activations