© 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. 17-GEMMASCOPE-2-RES-16K
    7. 11169
    Prev
    Next
    INDEX
    Explanations

    switch case match

    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_17_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
    на
    2.81
    দ
    2.60
    পক্ষে
    2.29
    at
    2.21
    na
    2.07
    ל
    2.04
    ições
    1.95
    ંટ
    1.88
    fact
    1.88
    س
    1.86
    POSITIVE LOGITS
    ется
    2.48
     daarom
    2.30
    ファスナー
    2.25
     attendant
    2.10
     arrears
    2.07
     arrière
    2.06
    ος
    2.01
     blames
    1.98
     Pencil
    1.98
    ened
    1.98
    Activations Density 0.092%

    No Known Activations