© 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. 919
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

    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
     m
    0.74
     husk
    0.69
     s
    0.66
     businessmen
    0.63
     dm
    0.62
     morphology
    0.61
    행
    0.61
     ინტერ
    0.60
     diastere
    0.60
     toppings
    0.60
    POSITIVE LOGITS
    Flexible
    0.81
    Rew
    0.80
    Salary
    0.80
    Invoice
    0.79
    Contract
    0.77
    ﺼ
    0.76
    Да
    0.75
     रे
    0.75
    ᱞ
    0.74
    Toilet
    0.74
    Activations Density 0.001%

    No Known Activations