© 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. 2640
    Prev
    Next
    INDEX
    Explanations

    explanation and considerations

    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
    s
    8.46
    ي
    7.69
    т
    7.02
    ו
    6.85
    ০
    6.85
    e
    6.55
    ੀ
    6.41
    ン
    6.37
    ে
    6.36
    i
    6.29
    POSITIVE LOGITS
    KindOfClass
    3.99
    обходимо
    3.41
    𝚒
    3.06
    theless
    3.01
    дцать
    2.99
    𝚍
    2.97
    ductory
    2.93
    которые
    2.85
    𝚎
    2.73
    𝚘
    2.71
    Activations Density 0.063%

    No Known Activations