© 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-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 981
    Prev
    Next
    INDEX
    Explanations

    most important / idiomatic

    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_9_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
    er
    3.03
     Dioxide
    2.69
    erai
    2.60
    tilde
    2.55
    в
    2.54
     dioxide
    2.51
    𝚛
    2.50
    𝚗
    2.46
    स्थल
    2.44
    ட்சத்திர
    2.40
    POSITIVE LOGITS
    s
    3.41
    aurant
    3.03
    aurants
    2.88
    sak
    2.75
    entimes
    2.69
    eban
    2.66
     safest
    2.60
     Lyapunov
    2.58
    いる
    2.55
    sellers
    2.46
    Activations Density 0.592%

    No Known Activations