© 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
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 5112
    Prev
    Next
    INDEX
    Explanations

    arrays and lists

    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_65k_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
     satta
    0.78
     bathrooms
    0.77
     bathroom
    0.77
     liquor
    0.76
     blackmail
    0.75
     Bathroom
    0.73
    酒
    0.73
    飲
    0.72
    agt
    0.71
    etry
    0.71
    POSITIVE LOGITS
     ArrayList
    1.27
    Arrays
    1.25
     Arrays
    1.23
    Array
    1.21
    ArrayList
    1.20
     arrays
    1.20
     Array
    1.20
     array
    1.18
    数组
    1.18
    arrays
    1.15
    Activations Density 1.035%

    No Known Activations