© 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. 757
    Prev
    Next
    INDEX
    Explanations

    Corrosion, coronary, coroutines, Corinthian, Corazón

    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
    ем
    0.84
    د
    0.84
    ement
    0.83
    ski
    0.82
    t
    0.82
     luci
    0.81
     joka
    0.80
     Pá
    0.77
    ූ
    0.77
    shakes
    0.77
    POSITIVE LOGITS
    coran
    1.28
    rugated
    1.19
    𝙇
    1.17
    ponding
    1.15
    onavirus
    1.11
    ponden
    1.11
    onavir
    1.10
     movingRect
    1.07
     reefs
    1.05
     reef
    1.04
    Activations Density 0.133%

    No Known Activations