© 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. 3870
    Prev
    Next
    INDEX
    Explanations

    stemming

    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
    Not in Any Lists

    No Comments

    Negative Logits
    라인
    1.70
    쉐
    1.66
     라
    1.52
    argu
    1.48
     고급
    1.47
    ùng
    1.47
    \}$,
    1.47
    꼴
    1.46
    나라
    1.43
     번
    1.43
    POSITIVE LOGITS
    getCurrent
    1.60
    enabled
    1.49
    yll
    1.43
    ्रीट
    1.41
     grieve
    1.39
     egress
    1.39
     respiration
    1.39
     intimacy
    1.37
    ureate
    1.36
    isements
    1.35
    Activations Density 0.000%

    No Known Activations