© 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-262K
    7. 11916
    Prev
    Next
    INDEX
    Explanations

    executive summary

    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_262k_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
    т
    3.55
    一个
    3.15
    原因
    2.98
     fact
    2.97
     proverbial
    2.80
     Notwithstanding
    2.77
    𝑻
    2.74
    な
    2.71
    𝑭
    2.64
    ../
    2.59
    POSITIVE LOGITS
    ted
    3.11
    𒌆
    2.88
    ر
    2.81
    ियत
    2.78
    pä
    2.75
    ತ್ತು
    2.71
    てください
    2.66
     dyads
    2.62
    िस्ट
    2.60
     prides
    2.60
    Activations Density 0.010%

    No Known Activations