© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14609
    Prev
    Next
    INDEX
    Explanations

    membership checking with `in`

    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
    sche
    3.29
    lane
    2.99
    ት
    2.98
    sman
    2.96
    sure
    2.92
    late
    2.89
    ্ম্ম
    2.81
    detailed
    2.80
    spr
    2.80
    mike
    2.73
    POSITIVE LOGITS
    फारिश
    2.89
    naire
    2.65
    xty
    2.59
    ﺩ
    2.49
    EMPL
    2.43
    esta
    2.35
     beth
    2.33
     kans
    2.23
     ma
    2.22
    ற்ற
    2.20
    Activations Density 0.007%

    No Known Activations