© 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. 1670
    Prev
    Next
    INDEX
    Explanations

    samhsa.gov or similar URLs

    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
     expose
    0.68
     exposing
    0.65
     exposed
    0.62
    塩
    0.59
    文
    0.58
    DSA
    0.57
     lương
    0.56
    zzo
    0.56
     exposes
    0.56
    ến
    0.55
    POSITIVE LOGITS
    할
    0.69
    uir
    0.66
     গেছে
    0.64
    nier
    0.64
     তাত
    0.62
     Punt
    0.60
     Firms
    0.60
    渀
    0.60
     furent
    0.59
     crou
    0.58
    Activations Density 0.412%

    No Known Activations