© 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. 1616
    Prev
    Next
    INDEX
    Explanations

    programming operations

    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
     noqa
    2.47
    ️⃣
    2.41
    MeToo
    2.09
    ્ય
    1.94
    ⃣
    1.84
    endif
    1.79
    ので
    1.76
    𝐁
    1.71
    𝐚
    1.70
    azität
    1.69
    POSITIVE LOGITS
    s
    2.51
    ের
    2.49
    ς
    2.41
    ات
    2.34
    ㅎ
    2.25
     rigid
    2.20
    т
    2.16
    ים
    2.13
    ກ
    2.11
    сь
    2.10
    Activations Density 0.088%

    No Known Activations