© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7499
    Prev
    Next
    INDEX
    Explanations

    startup costs, cutoff date, lookup table

    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
    र
    1.52
    Upload
    1.15
    upload
    1.08
     uplink
    1.02
    kinson
    1.00
    ीकृत
    0.99
     upward
    0.99
     outing
    0.99
    arm
    0.94
    ์
    0.92
    POSITIVE LOGITS
    ्स
    0.98
    casian
    0.97
     fastening
    0.96
     govori
    0.94
    REME
    0.93
    disconnected
    0.93
     procedures
    0.92
     방식
    0.92
    shop
    0.91
     accustomed
    0.91
    Activations Density 0.313%

    No Known Activations