© 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. 2791
    Prev
    Next
    INDEX
    Explanations

    staying up-to-date

    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
    gares
    0.84
    दो
    0.84
    wem
    0.82
    柰
    0.76
    ált
    0.76
    జేపీ
    0.75
    weiser
    0.74
    )}{
    0.73
    स्टल
    0.73
    łos
    0.72
    POSITIVE LOGITS
     modern
    0.80
     often
    0.79
     keep
    0.78
     updates
    0.77
     Contemporary
    0.74
     staying
    0.74
     keeps
    0.73
     update
    0.72
     keeping
    0.72
     আপডেট
    0.71
    Activations Density 0.027%

    No Known Activations