© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 7071
    Prev
    Next
    INDEX
    Explanations

    uncompleted sequences and their continuation

    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_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
    골
    0.76
    ława
    0.75
    ambda
    0.72
    atypes
    0.71
    irme
    0.70
    帀
    0.68
    acional
    0.68
    垓
    0.67
    ivariable
    0.66
    등급
    0.65
    POSITIVE LOGITS
     continuation
    2.26
     interrupted
    2.25
     interruption
    2.19
     Continuation
    2.11
    结束
    2.10
     interrom
    2.07
     interruptions
    2.07
    中断
    2.01
     interrump
    1.99
     termination
    1.97
    Activations Density 0.565%

    No Known Activations