© 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. 13149
    Prev
    Next
    INDEX
    Explanations

    common follow-ups for questions and statements

    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
    ೭
    1.26
    äische
    1.25
    十年
    1.23
    thirty
    1.22
     ذات
    1.20
    하여
    1.18
    äischen
    1.18
    prehensive
    1.17
    ۹
    1.16
    匁
    1.15
    POSITIVE LOGITS
     kinda
    1.63
    めっちゃ
    1.48
     weird
    1.37
     stuff
    1.36
     guys
    1.30
    เยอะ
    1.30
     bbq
    1.29
     shitty
    1.28
     crappy
    1.28
     dodgy
    1.28
    Activations Density 0.000%

    No Known Activations