© 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. 22-GEMMASCOPE-2-RES-16K
    7. 1037
    Prev
    Next
    INDEX
    Explanations

    software, tools, and frameworks

    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_22_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
     biopsies
    0.69
     inhibition
    0.65
     invitations
    0.65
    MNIST
    0.63
    ocken
    0.62
     contaminated
    0.61
     invit
    0.60
    荨
    0.60
    Invit
    0.59
     Eligible
    0.58
    POSITIVE LOGITS
     software
    2.02
     tool
    1.94
     tools
    1.86
    软件
    1.77
     Software
    1.76
    software
    1.74
     softwares
    1.73
    工具
    1.72
     herramienta
    1.72
    Software
    1.70
    Activations Density 3.260%

    No Known Activations