© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5192
    Prev
    Next
    INDEX
    Explanations

    custom printing and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_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
     Ikea
    0.88
    ストア
    0.81
     comprado
    0.81
    购物
    0.80
     comerciantes
    0.80
     Barclays
    0.79
    alat
    0.78
    喿
    0.78
     IKEA
    0.78
     magasins
    0.78
    POSITIVE LOGITS
    উ
    0.67
    istently
    0.58
    itiveness
    0.58
     warrants
    0.56
     requests
    0.55
     clientele
    0.53
     high
    0.52
     commitment
    0.52
     slit
    0.52
     उच्च
    0.52
    Activations Density 0.124%

    No Known Activations