© 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. 4067
    Prev
    Next
    INDEX
    Explanations

    lock and locking

    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
    ization
    2.81
    操
    2.63
    ᱴ
    2.58
    ती
    2.57
    ियोजना
    2.54
    gua
    2.53
    嶼
    2.53
     rer
    2.52
    色列
    2.51
    gia
    2.47
    POSITIVE LOGITS
    smith
    2.73
    αιο
    2.37
    omers
    2.35
    륵
    2.32
     عليه
    2.29
    ுத
    2.20
    탰
    2.17
     valide
    2.17
    ালো
    2.17
    raiser
    2.15
    Activations Density 0.027%

    No Known Activations