© 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. 2352
    Prev
    Next
    INDEX
    Explanations

    three followed by entity

    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
    د
    4.40
    nd
    4.30
    та
    3.90
    ️⃣
    3.79
    ت
    3.77
    ية
    3.74
    на
    3.56
    து
    3.48
    서
    3.46
    ся
    3.45
    POSITIVE LOGITS
     extol
    2.67
    ются
    2.65
     usher
    2.54
    assertThat
    2.53
     comprov
    2.43
     Dadurch
    2.42
     esté
    2.40
     وسهلا
    2.40
     linewidth
    2.40
     portrayal
    2.38
    Activations Density 0.033%

    No Known Activations