© 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. 13-GEMMASCOPE-2-RES-16K
    4. 9879
    Prev
    Next
    INDEX
    Explanations

    pushing and submitting

    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
    adex
    2.09
    ୈ
    1.94
    ા
    1.91
    पचारिक
    1.90
    ಾ
    1.89
    σιμοποι
    1.86
    া
    1.86
     PARTY
    1.81
    ༘
    1.78
    orgetown
    1.77
    POSITIVE LOGITS
    此之外
    2.62
    tim
    2.17
    timed
    2.14
    ところに
    2.10
    शाही
    2.09
    ski
    2.09
    drv
    2.08
    yyyy
    2.08
    ところで
    2.06
    manifold
    2.01
    Activations Density 0.243%

    No Known Activations