© 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-262K
    7. 20125
    Prev
    Next
    INDEX
    Explanations

    bash, nano, policy, network, add

    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
    定了
    0.65
    ዚ
    0.65
    臂
    0.61
     ponú
    0.61
    ==-
    0.60
     గుర్
    0.60
     escenarios
    0.59
    提供了
    0.59
    쌌
    0.58
     ಭೂ
    0.57
    POSITIVE LOGITS
     aldehyde
    0.72
    atsuki
    0.70
     iodine
    0.70
     duas
    0.70
    Compound
    0.70
    ٥
    0.69
     peptid
    0.68
     compound
    0.66
    compound
    0.66
     COMPO
    0.66
    Activations Density 0.005%

    No Known Activations