© 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. 2487
    Prev
    Next
    INDEX
    Explanations

    challenge

    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
    ्स
    4.73
    ר
    4.49
    s
    3.98
    ு
    3.69
    siniz
    3.52
    ları
    3.45
    nce
    3.43
    ted
    3.41
    skaya
    3.40
    yyyyyyyy
    3.33
    POSITIVE LOGITS
    ী
    4.69
    е
    3.18
    𝗲
    3.14
    𝗿
    2.97
    地方
    2.93
    การ
    2.91
    情况下
    2.87
    𝚛
    2.86
    ಾ
    2.86
    ice
    2.82
    Activations Density 0.288%

    No Known Activations