© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 3517
    Prev
    Next
    INDEX
    Explanations

    bold formatting markers

    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
     But
    0.90
     However
    0.84
     "
    0.78
     Rather
    0.76
     Imagine
    0.74
     Instead
    0.74
     Unlike
    0.72
     "...
    0.72
     Essentially
    0.71
     Interestingly
    0.70
    POSITIVE LOGITS
    (_
    0.99
    {(
    0.97
     indiquant
    0.91
    ([
    0.90
     हारा
    0.90
     recommande
    0.89
    ✓
    0.87
     ввести
    0.87
    」(
    0.87
    (&
    0.86
    Activations Density 0.187%

    No Known Activations