© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10448
    Prev
    Next
    INDEX
    Explanations

    percentages and discounts

    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_13_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
    м
    2.79
    ات
    2.27
    ми
    2.12
    yya
    2.10
    एनए
    1.93
    籲
    1.92
    yat
    1.91
    कर्ता
    1.90
    yah
    1.87
    y
    1.86
    POSITIVE LOGITS
    <0xD8>
    2.42
     hogy
    2.24
     приме
    2.20
    P
    2.12
    patan
    2.00
     UserDao
    1.97
    ન્ટ
    1.96
    cnt
    1.91
    ℍ
    1.90
    不对
    1.89
    Activations Density 0.095%

    No Known Activations