© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 2252
    Prev
    Next
    INDEX
    Explanations

    adds to plurals

    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
     fewer
    0.62
     thinner
    0.59
    بري
    0.59
    lighter
    0.58
    bro
    0.58
     hetero
    0.58
     quieter
    0.57
     과
    0.57
     older
    0.56
     kiến
    0.56
    POSITIVE LOGITS
    ede
    0.74
    нее
    0.61
     añade
    0.60
     मतदारसं
    0.60
    edi
    0.60
     brings
    0.59
     voegen
    0.59
     randomNumber
    0.59
    ัง
    0.58
     adds
    0.58
    Activations Density 0.270%

    No Known Activations