© 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. 5384
    Prev
    Next
    INDEX
    Explanations

    active, running, open, ongoing

    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
     içeren
    1.35
    ्स
    1.28
    ため
    1.22
     hastened
    1.22
    ために
    1.21
    ول
    1.21
    𝚔
    1.15
     hasty
    1.13
     senseless
    1.13
    컥
    1.13
    POSITIVE LOGITS
     embers
    1.51
     partielle
    1.30
    fulness
    1.27
     रहने
    1.23
     Poh
    1.20
     busting
    1.19
     stati
    1.18
    時点
    1.18
     रहकर
    1.18
     attivo
    1.15
    Activations Density 0.356%

    No Known Activations