© 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. 10767
    Prev
    Next
    INDEX
    Explanations

    simulating, simulated, simplicity

    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
     subjected
    1.10
     single
    1.03
    ક
    1.02
    すぐに
    1.00
    必要がある
    0.98
    𝑵
    0.96
     riguarda
    0.96
    ्यक्रम
    0.94
    καν
    0.94
     ते
    0.93
    POSITIVE LOGITS
     annealing
    1.82
    ت
    1.60
    plicity
    1.44
    ultaneous
    1.44
    ulating
    1.36
    تون
    1.32
    monds
    1.31
    sim
    1.26
    onds
    1.25
    ulated
    1.24
    Activations Density 0.080%

    No Known Activations