© 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. 3983
    Prev
    Next
    INDEX
    Explanations

    Software development and interest rates

    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
    ————————————————
    3.78
    ————————
    3.62
    ————
    2.99
    ை
    2.96
    ———
    2.77
    ্ম্ম
    2.77
    كيد
    2.74
    araj
    2.68
    ⁧
    2.64
     encar
    2.63
    POSITIVE LOGITS
    tier
    2.64
    
    2.50
    det
    2.47
    फारिश
    2.45
    tare
    2.37
    gal
    2.33
    dr
    2.29
    ܛ
    2.25
    <em>
    2.25
    GAL
    2.23
    Activations Density 0.010%

    No Known Activations