© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 1719
    Prev
    Next
    INDEX
    Explanations

    stores, reserves, or collections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_width_262k_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
    یل
    0.50
    ί
    0.47
    لي
    0.47
    iders
    0.43
    образова
    0.43
    .(
    0.42
    Luk
    0.42
    elligent
    0.42
     telescop
    0.41
    mV
    0.41
    POSITIVE LOGITS
    ล
    0.71
    ي
    0.68
    i
    0.66
    י
    0.64
     reserves
    0.63
     coffers
    0.60
     assets
    0.59
     inventory
    0.56
     estoque
    0.56
     запас
    0.55
    Activations Density 0.161%

    No Known Activations