© 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. 652
    Prev
    Next
    INDEX
    Explanations

    what should i do

    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
    kä
    1.25
    ت
    1.13
    avro
    1.13
    lp
    1.03
    trou
    1.03
     இருந்து
    1.03
    taught
    1.02
    ியுள்ள
    1.00
    stro
    1.00
    '";
    1.00
    POSITIVE LOGITS
    omsday
    1.49
     differently
    1.25
    ppel
    1.22
     wrong
    1.22
     wonders
    1.20
    鹃
    1.18
    ငန်း
    1.12
     acrylate
    1.12
     ashore
    1.11
    Ğ
    1.11
    Activations Density 0.048%

    No Known Activations