© 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. 76131
    Prev
    Next
    INDEX
    Explanations

    confiscate, requisition, seize property

    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
    HQ
    -0.81
    ineno
    -0.79
    று
    -0.76
    ($__
    -0.76
    >',
    -0.75
     dropping
    -0.74
    usehen
    -0.73
    setGravity
    -0.73
    ∕
    -0.71
     $(
    -0.71
    POSITIVE LOGITS
     expropri
    2.63
     confiscated
    1.52
     confis
    1.44
     confiscation
    1.41
     compulsory
    1.29
     commande
    1.23
     seizure
    1.23
     compensation
    1.23
     requisition
    1.21
     compul
    1.18
    Activations Density 0.016%

    No Known Activations