© 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. 715
    Prev
    Next
    INDEX
    Explanations

    want me

    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
    o
    1.25
     alınan
    1.23
    tidak
    1.23
    শত
    1.20
     två
    1.19
     żad
    1.18
     kaks
    1.14
     ikke
    1.14
     not
    1.13
     yapılacak
    1.13
    POSITIVE LOGITS
     ہیں
    1.30
    <bos>
    1.28
     встречаются
    1.22
     ہیں۔
    1.17
     constitute
    1.15
     nên
    1.15
    केज
    1.15
     setLayout
    1.15
     designation
    1.14
     betreff
    1.14
    Activations Density 2.485%

    No Known Activations