© 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. 858
    Prev
    Next
    INDEX
    Explanations

    allows, Can, defeats, makes

    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
    marginTop
    1.30
    那个
    1.22
     bora
    1.22
     loyal
    1.18
    ১
    1.16
    ជាង
    1.12
    なります
    1.10
     inseparable
    1.09
     aveva
    1.09
     zn
    1.08
    POSITIVE LOGITS
    تش
    1.27
    ت
    1.19
    تع
    1.18
    ழ்பெற்ற
    1.11
    IRQHandler
    1.11
    تي
    1.10
    Cannot
    1.10
    ಸ್ಪ
    1.06
    lach
    1.05
    社
    1.04
    Activations Density 0.000%

    No Known Activations