© 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. 7659
    Prev
    Next
    INDEX
    Explanations

    aquelarre

    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
    з
    1.23
    წ
    1.15
    ز
    1.02
    него
    1.02
    Thông
    1.00
     Przed
    1.00
    Mem
    1.00
    ição
    1.00
    PRESS
    0.99
    åk
    0.98
    POSITIVE LOGITS
    図
    1.15
     Corollary
    1.12
    в
    1.09
     households
    1.08
    ornia
    1.07
     EditText
    1.05
     pajamas
    1.03
     Tasmania
    1.02
    ब्दिक
    1.00
     vein
    1.00
    Activations Density 0.001%

    No Known Activations