© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9425
    Prev
    Next
    INDEX
    Explanations

    .hk, .com, .org

    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
    िया
    1.87
    チュラル
    1.50
    Limitations
    1.40
    caps
    1.38
    vät
    1.38
    siehe
    1.37
    وڈ
    1.36
     δ
    1.33
     {};
    1.32
     বলিয়া
    1.30
    POSITIVE LOGITS
    ᐟ
    1.47
    %.
    1.47
    ा
    1.46
    sized
    1.45
    ೂರ
    1.44
     dorado
    1.44
    0
    1.44
    s
    1.43
    个月
    1.43
    ्स
    1.41
    Activations Density 0.118%

    No Known Activations