© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 10849
    Prev
    Next
    INDEX
    Explanations

    rip etal

    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
    𝑮
    2.70
    msubsup
    2.66
    नांतर
    2.65
    рани
    2.56
    munderover
    2.54
     contours
    2.48
    条件的
    2.46
    irono
    2.40
    arrow
    2.38
    ंना
    2.36
    POSITIVE LOGITS
    ษา
    2.23
    Taxi
    2.17
    떼
    2.09
    ধরনের
    2.08
    Globe
    2.08
    াল্ড
    2.06
    crollView
    2.02
    huy
    2.02
    oslav
    2.01
     인사
    2.00
    Activations Density 0.007%

    No Known Activations