© 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. 83159
    Prev
    Next
    INDEX
    Explanations

    locking and blocking

    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
    接到
    -0.86
    불
    -0.82
    Piper
    -0.75
    烧
    -0.75
    渐
    -0.74
     hiding
    -0.73
    varnothing
    -0.73
    rotech
    -0.72
    Perry
    -0.71
     Zer
    -0.71
    POSITIVE LOGITS
     lock
    2.58
     locks
    2.30
     Lock
    2.02
    lock
    1.98
     LOCK
    1.95
     locking
    1.95
    Lock
    1.88
     Locks
    1.83
     locked
    1.83
    Locks
    1.82
    Activations Density 0.065%

    No Known Activations