© 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. 13-GEMMASCOPE-2-RES-16K
    7. 2530
    Prev
    Next
    INDEX
    Explanations

    turn boundary 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_13_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
    timepoint
    1.05
    膻
    0.99
    ற்புத
    0.98
    Variance
    0.97
     thug
    0.96
    論
    0.96
    𐱃
    0.95
     길
    0.95
    女
    0.94
    궪
    0.94
    POSITIVE LOGITS
    s
    0.64
     "
    0.61
     and
    0.61
     lives
    0.59
     incrementally
    0.58
    à
    0.58
     commitment
    0.56
    u
    0.55
     every
    0.55
     (
    0.54
    Activations Density 0.008%

    No Known Activations