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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 117685
    Prev
    Next
    INDEX
    Explanations

    particulate matter

    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
    ない
    0.61
    م
    0.61
    ม
    0.61
    ками
    0.60
    รี
    0.59
    ร
    0.59
    از
    0.58
    INSON
    0.58
    ر
    0.57
    ता
    0.56
    POSITIVE LOGITS
    banks
    0.66
    customers
    0.63
    uq
    0.59
    savings
    0.59
    era
    0.58
     svým
    0.57
    ed
    0.56
    ffffff
    0.56
     zespo
    0.56
    ùi
    0.55
    Activations Density 0.000%

    No Known Activations