© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12957
    Prev
    Next
    INDEX
    Explanations

    fish or gradient

    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
    Negative Logits
    磋
    2.64
    ок
    2.29
    ongrass
    2.23
    injlim
    2.19
    躇
    2.18
    `(
    2.12
    incent
    2.12
     Bxe
    2.11
    allocate
    2.06
    lowing
    2.04
    POSITIVE LOGITS
    لد
    2.32
    ້ອງ
    2.26
    𝙍
    2.24
    পন্থী
    2.24
    نظر
    2.15
    ސް
    2.12
     نظر
    2.05
    तार
    2.03
     SqlParameter
    2.02
     mộ
    1.99
    Activations Density 0.179%

    No Known Activations