© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 886
    Prev
    Next
    INDEX
    Explanations

    also and addition

    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
     eben
    1.65
    ্স
    1.64
    ifiably
    1.57
    й
    1.49
    ritten
    1.48
    zelfde
    1.47
    दार
    1.47
    ところに
    1.42
    ות
    1.41
     raya
    1.40
    POSITIVE LOGITS
    ب
    1.85
     불구하고
    1.81
    ষুধ
    1.75
     самое
    1.71
    तरी
    1.62
    ج
    1.59
    یت
    1.56
    য়ের
    1.56
    য়ের
    1.51
    𝐥
    1.50
    Activations Density 0.347%

    No Known Activations