© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2205
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

    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
    en
    3.47
    ের
    3.05
    ر
    2.97
    s
    2.74
    enian
    2.69
    م
    2.65
    ्स
    2.56
    ৮
    2.55
    nın
    2.48
    的目的
    2.48
    POSITIVE LOGITS
    ്രീ
    2.10
     bogey
    2.07
    б
    1.90
    т
    1.87
     Notwithstanding
    1.85
    bereich
    1.79
    бля
    1.78
    cA
    1.75
     κυ
    1.73
    SG
    1.72
    Activations Density 0.021%

    No Known Activations