Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-262K
    4. 6364
    Prev
    Next
    INDEX
    Explanations

    microsoft products

    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_262k_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
    не
    1.02
    к
    0.89
     dif
    0.86
    း
    0.83
    д
    0.82
    п
    0.78
    ‍♂️
    0.78
     снима
    0.76
    м
    0.76
    hbar
    0.75
    POSITIVE LOGITS
    VisualStudio
    1.39
     Azure
    1.36
    Azure
    1.20
     OneDrive
    1.19
     Nauchno
    1.13
    <unused176>
    1.13
    शरी
    1.12
    sulfanyl
    1.09
     Lumia
    1.09
    ié
    1.08
    Activations Density 0.029%

    No Known Activations