© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7234
    Prev
    Next
    INDEX
    Explanations

    in followed byin followed by locationin followed by prepositionsin followed by positionin followed by prepositional phrases

    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_22_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
    د
    1.15
    在
    1.15
    gf
    1.09
     внутрен
    1.06
    क
    1.06
    此事
    1.05
    deel
    0.99
    கள்
    0.98
     इनमें
    0.96
    ിൽ
    0.95
    POSITIVE LOGITS
     நு
    0.94
    느
    0.89
    \!
    0.88
    скага
    0.87
     vào
    0.87
     factored
    0.86
     establecidos
    0.85
     pareja
    0.84
     tức
    0.83
     makarna
    0.83
    Activations Density 0.049%

    No Known Activations