© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 9056
    Prev
    Next
    INDEX
    Explanations

    expressing unique integers

    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_17_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
     shrimps
    0.93
    景色
    0.92
     Austrian
    0.90
    深圳
    0.90
     orthodontic
    0.90
    computation
    0.90
    {
    0.90
    ਰ
    0.88
     Fiji
    0.88
     ചെയ്തു
    0.87
    POSITIVE LOGITS
    밭
    1.14
     targeting
    1.13
    用於
    1.09
     Öz
    1.08
    obiettivo
    1.04
    컴
    1.03
    itinéraire
    1.03
    ivia
    1.03
    ALD
    1.02
     answers
    1.01
    Activations Density 0.009%

    No Known Activations