© 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. 4004
    Prev
    Next
    INDEX
    Explanations

    remember that

    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
    ar
    3.26
    ᴅ
    3.22
     ṣe
    3.09
    arid
    2.91
    𝙜
    2.88
    𝙙
    2.86
    HideFlags
    2.77
    OutputStream
    2.75
    asche
    2.70
    𝙨
    2.64
    POSITIVE LOGITS
    ências
    2.85
    toc
    2.71
    trag
    2.63
    nent
    2.58
    sie
    2.57
    nen
    2.57
    rn
    2.57
    tom
    2.53
    ..</
    2.51
    lli
    2.50
    Activations Density 0.028%

    No Known Activations