© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 101657
    Prev
    Next
    INDEX
    Explanations

    packing efficiency and rate

    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_all/layer_41_width_262k_l0_big
    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
     ҳо
    0.41
    PROM
    0.40
     хо
    0.38
    த்துடன்
    0.38
     homozygous
    0.38
    curité
    0.37
     인증
    0.37
    }=[
    0.36
     तीर
    0.36
    飆
    0.36
    POSITIVE LOGITS
     packing
    1.77
     Packing
    1.72
    Packing
    1.68
    packing
    1.54
     पैकिंग
    1.45
     packer
    1.31
     packers
    1.26
     unpacking
    1.23
    pack
    1.22
     packed
    1.22
    Activations Density 0.001%

    No Known Activations