© 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. 5162
    Prev
    Next
    INDEX
    Explanations

    links, URLs, and specific terms

    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
    ت
    1.29
    с
    1.20
    ма
    1.11
    т
    1.09
    usic
    1.07
    н
    1.05
     Scotia
    1.05
    риди
    1.02
    ępuje
    1.02
     نړ
    1.02
    POSITIVE LOGITS
     shutil
    1.27
    噜
    1.18
    ➝
    1.12
    イー
    1.12
     boobs
    1.11
     ganancias
    1.11
     appuy
    1.10
     sicherlich
    1.10
     tasteless
    1.10
     betrokken
    1.08
    Activations Density 0.002%

    No Known Activations