© 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. 2319
    Prev
    Next
    INDEX
    Explanations

    after time-related events

    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
     तब
    0.90
    avenir
    0.87
     pasir
    0.80
    ع
    0.79
    જર
    0.78
     கீழ்
    0.78
    ിലേക്ക്
    0.78
    номер
    0.77
    др
    0.77
    前
    0.76
    POSITIVE LOGITS
    noons
    1.14
    math
    1.06
    WARDS
    1.03
     shave
    1.02
    words
    1.02
     awhile
    0.98
    thoughts
    0.96
    ward
    0.96
    wards
    0.94
    effects
    0.91
    Activations Density 0.081%

    No Known Activations