© 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. 2687
    Prev
    Next
    INDEX
    Explanations

    file opening modes 'r' and 'w'

    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
    y
    3.66
    u
    3.30
    a
    3.25
    i
    2.98
    in
    2.94
    e
    2.87
    t
    2.83
    o
    2.80
    d
    2.76
    ا
    2.66
    POSITIVE LOGITS
    𝚎
    2.07
    glightbox
    2.01
    𝐧
    1.98
    𝐫
    1.97
    targetReference
    1.94
    𝐞
    1.90
    𝐠
    1.85
    timevals
    1.79
    𝐥
    1.78
    branchNode
    1.78
    Activations Density 0.121%

    No Known Activations