© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 5779
    Prev
    Next
    INDEX
    Explanations

    program execution and logic

    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
     shenanigans
    0.72
    ^*
    0.66
    Advanced
    0.65
    杩
    0.65
     Attendees
    0.64
    atcher
    0.63
     अत्याधुनिक
    0.62
    ꯕ
    0.62
    эль
    0.62
    མ་
    0.62
    POSITIVE LOGITS
     Download
    0.71
     download
    0.67
     Troy
    0.67
    Upload
    0.66
     programme
    0.66
     program
    0.65
     Bure
    0.64
    下载
    0.62
     downloads
    0.62
     mañana
    0.62
    Activations Density 0.190%

    No Known Activations