© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 73317
    Prev
    Next
    INDEX
    Explanations

    memory access control

    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
    颊
    -0.77
     vasca
    -0.73
    芯
    -0.73
     Beschreibung
    -0.70
    kaner
    -0.70
     setDescription
    -0.69
     commitments
    -0.69
    栋
    -0.68
     blockage
    -0.68
    engage
    -0.67
    POSITIVE LOGITS
     address
    1.13
     Address
    1.12
     data
    1.05
    Address
    1.04
    address
    1.02
     ADDRESS
    1.01
     WRITE
    1.00
    DATA
    0.97
     bus
    0.96
    data
    0.95
    Activations Density 0.018%

    No Known Activations