© 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. 3942
    Prev
    Next
    INDEX
    Explanations

    overall assessment and summary

    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
    ا
    2.90
    اا
    2.82
    ત્મ
    2.75
    LowerCase
    2.45
    es
    2.44
    ا۔
    2.43
    ات
    2.43
    اث
    2.40
    ային
    2.33
    onics
    2.27
    POSITIVE LOGITS
    𝐬
    3.35
    rzym
    2.82
     gla
    2.77
    𝐢
    2.71
    𝐠
    2.71
    𝐜
    2.62
    𝐲
    2.61
     ST
    2.60
    ST
    2.57
    ับสนุน
    2.54
    Activations Density 0.072%

    No Known Activations