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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 133937
    Prev
    Next
    INDEX
    Explanations

    packing and unpacking

    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_40_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
     stored
    0.42
    stored
    0.39
    摄
    0.38
    lollipop
    0.38
    quées
    0.38
    魑
    0.38
    Throughout
    0.37
    競
    0.36
    фов
    0.36
    рующий
    0.36
    POSITIVE LOGITS
     packing
    2.11
     Packing
    1.98
    Packing
    1.98
    packing
    1.85
     पैकिंग
    1.65
     packer
    1.53
     packers
    1.48
     packed
    1.41
    Pack
    1.39
    pack
    1.38
    Activations Density 0.042%

    No Known Activations