© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 18445
    Prev
    Next
    INDEX
    Explanations

    words meaning "after" or sequential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
     bustle
    0.65
    စျေး
    0.64
    ⼈
    0.63
     букмекерлер
    0.63
    ेंसिल
    0.61
    চৈতন্যের
    0.61
    હિતી
    0.60
     organising
    0.57
    keye
    0.57
    အစိတ်အပိုင်း
    0.57
    POSITIVE LOGITS
     después
    0.73
     verschied
    0.70
    )
    0.70
     depois
    0.67
    Después
    0.63
     després
    0.63
     había
    0.62
     setelah
    0.62
     testicule
    0.61
     médicaments
    0.61
    Activations Density 0.451%

    No Known Activations