© 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-262K
    7. 5573
    Prev
    Next
    INDEX
    Explanations

    .com domains in French contexts

    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
     getting
    0.81
     돌아
    0.80
     ผู้
    0.79
     kemenangan
    0.78
     best
    0.78
     Legislative
    0.77
     got
    0.77
    贏
    0.77
     mga
    0.77
     مصروف
    0.76
    POSITIVE LOGITS
     notamment
    1.31
    éc
    1.19
    Université
    1.12
    œur
    1.06
     ét
    1.05
    bourg
    1.05
    être
    1.03
     pour
    1.03
    abilité
    1.02
    sous
    1.01
    Activations Density 0.003%

    No Known Activations