© 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. 2960
    Prev
    Next
    INDEX
    Explanations

    base to con

    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
     based
    0.75
     outside
    0.70
     similarly
    0.67
     constructs
    0.67
    ব
    0.67
     engages
    0.65
    ສາ
    0.65
    ুৎ
    0.65
     signaled
    0.65
    ॉन
    0.64
    POSITIVE LOGITS
     yang
    1.01
     dell
    0.95
    ในการ
    0.91
     nell
    0.90
    ที่ไม่
    0.89
    ที่
    0.88
     untuk
    0.84
     những
    0.84
     nella
    0.81
     並
    0.81
    Activations Density 0.307%

    No Known Activations