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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3072
    Prev
    Next
    INDEX
    Explanations

    0.2

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-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
     Procurement
    0.93
    枸
    0.89
    指標
    0.89
     Canvas
    0.86
    Vod
    0.86
     Organizations
    0.86
     Coding
    0.85
    换
    0.84
     AFFA
    0.84
     đổi
    0.83
    POSITIVE LOGITS
     impress
    0.67
     black
    0.67
     denn
    0.65
     comfort
    0.62
    irai
    0.62
     doute
    0.61
    ilmente
    0.58
     ибо
    0.58
     diameter
    0.57
     seguro
    0.57
    Activations Density 0.001%

    No Known Activations