© 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. 911
    Prev
    Next
    INDEX
    Explanations

    the specific

    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
     часа
    1.63
     sobald
    1.62
    谛
    1.57
    𝓭
    1.48
     राजन
    1.41
     मैप
    1.40
     laget
    1.39
     chute
    1.39
     Тому
    1.38
     messa
    1.36
    POSITIVE LOGITS
    ığı
    1.57
    𝚜
    1.45
    ~/
    1.44
    Vý
    1.39
    𝚢
    1.37
    வ்
    1.37
    issé
    1.36
    ակ
    1.35
    ности
    1.34
    dispers
    1.34
    Activations Density 0.146%

    No Known Activations