© 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-65K
    7. 5215
    Prev
    Next
    INDEX
    Explanations

    psychology, health, and capacity

    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
     Local
    0.86
    P
    0.83
    G
    0.80
     Temporal
    0.79
     Terminal
    0.79
    K
    0.78
    B
    0.78
     Primary
    0.78
     Structure
    0.78
     Shipping
    0.78
    POSITIVE LOGITS
    孅
    1.13
    itiers
    1.09
     trastornos
    1.07
     laude
    1.04
    usional
    1.03
    🔛
    1.03
    ujjati
    1.03
    enerbah
    1.01
    🔜
    1.01
    orpio
    1.00
    Activations Density 0.020%

    No Known Activations