© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49729
    Prev
    Next
    INDEX
    Explanations

    blister pack, carded, box, packaging

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enable
    -0.82
    AddressBook
    -0.78
     conquest
    -0.74
    Exclude
    -0.73
     اضط
    -0.73
    箪
    -0.71
     عز
    -0.71
     貨
    -0.70
    cores
    -0.68
     روسی
    -0.68
    POSITIVE LOGITS
     blister
    2.00
     blisters
    1.41
     бли
    1.19
    bli
    1.09
     HEADER
    1.02
    sealed
    0.93
     sealed
    0.93
     Header
    0.93
     bli
    0.91
    carded
    0.91
    Activations Density 0.032%

    No Known Activations