© 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. 12729
    Prev
    Next
    INDEX
    Explanations

    dust and particles

    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
     tone
    1.16
     tones
    1.16
    青春
    1.12
     والإ
    1.11
     sentimento
    1.07
     موج
    1.06
    俪
    1.04
     temperatur
    1.04
    ⎥
    1.03
     läbi
    1.03
    POSITIVE LOGITS
     Elite
    0.95
    A
    0.93
     sift
    0.93
     particles
    0.93
    мель
    0.92
    r
    0.89
     debris
    0.88
    particles
    0.88
    Election
    0.84
    筛
    0.84
    Activations Density 0.177%

    No Known Activations