© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 103659
    Prev
    Next
    INDEX
    Explanations

    constraining or restricting

    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
     墊
    -0.75
    éviter
    -0.74
    衮
    -0.73
     vượt
    -0.72
    ason
    -0.71
     roze
    -0.71
     éviter
    -0.69
    kách
    -0.69
    례
    -0.69
    ctors
    -0.68
    POSITIVE LOGITS
     constraints
    3.67
     restrictions
    3.64
     constraint
    3.58
     restriction
    3.53
    限制
    3.31
     restricting
    3.28
     constrain
    3.27
     restrict
    3.23
     restrictive
    3.17
     restraints
    3.03
    Activations Density 0.080%

    No Known Activations