© 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
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-16K
    4. 442
    Prev
    Next
    INDEX
    Explanations

    list item marker

    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_29_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
    ាម
    0.56
    Table
    0.54
    Building
    0.54
    ਆ
    0.53
    કી
    0.52
    annual
    0.52
    Investor
    0.52
    Auth
    0.51
    Forecast
    0.51
    દ
    0.51
    POSITIVE LOGITS
     sī
    0.57
     Tere
    0.56
     lesen
    0.53
     decorated
    0.53
     upon
    0.52
     nėra
    0.52
    ปลี่ยน
    0.52
    俬
    0.52
     chr
    0.51
    <unused1049>
    0.51
    Activations Density 1.588%

    No Known Activations