© 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. 7-GEMMASCOPE-2-RES-16K
    7. 10310
    Prev
    Next
    INDEX
    Explanations

    innerHTML assignment

    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
    Negative Logits
    ੍ਹ
    2.95
    ཾ
    2.59
    렇
    2.45
    𝑧
    2.44
    áf
    2.40
    𝑦
    2.39
    𝒹
    2.39
    otland
    2.38
    ্ম্ম
    2.37
    CreateTable
    2.35
    POSITIVE LOGITS
    sg
    2.79
    overy
    2.65
    tow
    2.54
    she
    2.52
     \[
    2.52
    nya
    2.49
    speople
    2.48
    ので
    2.47
    ee
    2.40
    tamil
    2.38
    Activations Density 0.013%

    No Known Activations