© 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-16K
    7. 542
    Prev
    Next
    INDEX
    Explanations

    python code snippets

    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
    grocery
    0.74
    ️
    0.72
    eer
    0.71
    oretically
    0.70
    ्य
    0.68
    ্বর
    0.66
    heartedly
    0.66
    كية
    0.64
     مقابل
    0.64
    lifestyle
    0.63
    POSITIVE LOGITS
    𝖚
    0.59
     UIStoryboard
    0.58
    绶
    0.57
     spezielle
    0.57
     neue
    0.56
     জাপান
    0.56
    сл
    0.55
     roślin
    0.55
     eigenfunctions
    0.55
     vicino
    0.54
    Activations Density 3.292%

    No Known Activations