© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1558
    Prev
    Next
    INDEX
    Explanations

    years old

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +}$
    2.14
    其中包括
    1.92
    ای
    1.91
     বসে
    1.82
    বর্তমানে
    1.79
    ,...,
    1.69
     laureate
    1.69
     mour
    1.68
     nasz
    1.67
    홧
    1.66
    POSITIVE LOGITS
    y
    2.79
    t
    2.66
    िंग
    2.43
    aabb
    2.10
    tte
    2.07
     μην
    2.05
    ेटिक
    1.99
    sus
    1.99
    ture
    1.98
    tım
    1.94
    Activations Density 0.051%

    No Known Activations