© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4407
    Prev
    Next
    INDEX
    Explanations

    multi-faceted, multi-step, multiple channels

    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
    ਨੀ
    1.91
    sw
    1.81
    м
    1.71
    岖
    1.69
    al
    1.67
    ো
    1.67
    ско
    1.65
    ما
    1.65
    гант
    1.62
    ో
    1.59
    POSITIVE LOGITS
     sclerosis
    3.79
     myeloma
    3.53
     deles
    2.38
    IPLE
    2.38
    संख्यक
    2.37
     اللهم
    2.35
    𝙩
    2.29
    pubmed
    2.19
    faceted
    2.15
    ieurs
    2.15
    Activations Density 0.107%

    No Known Activations