© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3303
    Prev
    Next
    INDEX
    Explanations

    conditional code keywords

    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
    ιβ
    2.82
    س
    2.75
    т
    2.67
    s
    2.54
    NER
    2.45
    으로
    2.41
    ों
    2.41
    Bl
    2.36
    േ
    2.35
    மிய
    2.35
    POSITIVE LOGITS
    FromNib
    2.73
     dậy
    2.41
    olute
    2.32
    بیداری
    2.31
    ◟
    2.22
     liberty
    2.21
    hty
    2.18
     Frieden
    2.17
    world
    2.16
    𝑙
    2.14
    Activations Density 0.038%

    No Known Activations