© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1652
    Prev
    Next
    INDEX
    Explanations

    earning potential per hour or month

    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
    omitempty
    3.03
    儡
    2.66
    ͯ
    2.65
    䔀
    2.54
    𝘁
    2.54
     {!
    2.49
    propylene
    2.47
    佔
    2.47
    ーション
    2.46
    ないので
    2.43
    POSITIVE LOGITS
    i
    5.02
    ه
    4.99
    ে
    4.31
    н
    4.23
    ي
    4.15
    a
    4.02
    м
    3.99
    aing
    3.71
    ン
    3.62
    ر
    3.59
    Activations Density 0.068%

    No Known Activations