© 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-262K
    7. 10124
    Prev
    Next
    INDEX
    Explanations

    China and Chinese

    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
    ו
    3.29
    ই
    2.95
    ১
    2.55
    िंग
    2.49
    tedir
    2.39
    ක්
    2.38
    teen
    2.33
    theless
    2.30
    תי
    2.28
    ું
    2.26
    POSITIVE LOGITS
    at
    3.15
    на
    2.91
     indel
    2.43
    𝒅
    2.43
     واحد
    2.42
    emers
    2.38
     willing
    2.38
    u
    2.36
    ви
    2.33
    }^{-}$
    2.31
    Activations Density 0.119%

    No Known Activations